speech to text live stream

Online Live Audio Transcriber Tool

One Click Accurate Real-Time Transcription with ScreenApp for Lectures, Meetings, and More

• Real-Time Transcription
• Free and Online
• Works on lectures, meetings

Trusted and Supported by businesses across the world

Getting Started with ScreenApp's Live Audio Transcriber

ScreenApp's Live Audio Transcriber Tool offers a seamless way to convert audio into text in real-time. Follow these simple steps to get started:

1. Start Recording

Click on the "Start Recording" button to begin capturing audio input. Ensure that your microphone is properly connected and accessible to your web browser.

2. Transcription in Progress

As soon as you start speaking or playing audio, the tool's advanced speech recognition technology will kick in, transcribing the audio into text instantly. Watch as the transcript appears on your screen in real-time, keeping pace with the spoken words.

3.Review and Customize

During the transcription process, you can pause, resume, or stop the recording as needed. The tool provides various customization options, such as adjusting the font size or style, to enhance readability.

4. Export or Copy

Once the transcription is complete, you can easily copy the text to your clipboard or download the transcript in various formats like PDF or TXT. This allows you to seamlessly integrate the transcripts into your workflows or share them with others.

That's it! With ScreenApp's Live Audio Transcriber Tool, you can effortlessly transcribe lectures, meetings, interviews, podcasts, and more, without any hassle or delays. Start experiencing the power of real-time transcription today!

Benefits of this Live Audio Transcriber

✓ one-click transcription.

Start transcribing live audio with just a single click, making it incredibly convenient and user-friendly.

✓ Free and No Downloads

Enjoy a free online service without the need for any downloads or software installations, making it accessible from anywhere.

✓ Real-Time and Instant

Experience seamless real-time transcription, instantly converting spoken words into text as they're uttered.

✓ Unlimited Transcription

Transcribe without limits, whether it's for lectures, meetings, interviews, podcasts, or any other audio content.

✓ Downloadable Transcripts

Easily download transcripts in various formats for further editing, sharing, or archiving.

✓ Advanced Features

Sign up for premium features like speaker diarization, which separates and labels multiple speakers for enhanced organization.

✓ Versatile Applications

Transcribe lectures, presentations, meetings, interviews, videos, and more, making it a versatile tool for various purposes.

✓ Industry-Leading Accuracy

Benefit from cutting-edge speech recognition technology that ensures highly accurate transcriptions.

✓ Multi-Language Support

Transcribe audio in multiple languages, expanding the tool's reach and accessibility.

✓ Customizable Outputs

Tailor transcripts to your specific needs with customizable formatting options and styling.

✓ Privacy and Security

Enjoy peace of mind with robust privacy and security measures to protect your sensitive audio data.

✓ Integration Capabilities

Seamlessly integrate the transcription tool with other applications or workflows for enhanced productivity.

Online Screen Recorder

Capture your screen and camera in a click without a watermark, including any Teams, Meet, Zoom, or Webex Call.

Transcribe in a Flash

Transcribe any video or audio with AI and without lifting a finger with 99% accuracy and lightning speed.

Summarize Recordings with AI

Save time and effort. Get an AI-generated summary automatically and focus on what matters.

Automatic Notes with AI

Turn your videos and audio into skimmable notes. Click to the part you want to watch.

Chat to Your Recordings

Instantly extract action items, decisions, and insights from your recordings. It's like talking to somebody who has watched the videos for you.

Instantly Record Audio and Video

Record your audio and Video with 1 click directly from your browser.

Translate Videos with AI

Translate Understand any video or audio in over 50 languages.

Upload any Video or Audio

Upload any video or audio file for transcription, summaries and notes.

Enhancing Learning and Accessibility

For those seeking accurate and efficient transcription of lectures, presentations, or classroom discussions, ScreenApp's tool offers a seamless solution. With its real-time transcription capabilities, students and educators can effortlessly capture every word spoken, ensuring no crucial information is missed. This not only enhances note-taking and comprehension but also promotes accessibility for individuals with disabilities or learning challenges.

Boosting Professional Productivity

In the professional realm, ScreenApp's Live Audio Transcriber Tool streamlines collaboration and information sharing among teams. Whether it's transcribing meetings, interviews, or conferences, this tool ensures accurate record-keeping and eliminates the need for manual note-taking, boosting productivity. Businesses can leverage its capabilities to improve communication, decision-making, and overall efficiency.

Empowering Writers and Researchers

For journalists, writers, and researchers, the tool proves invaluable in transcribing interviews, podcasts, focus groups, and field recordings. With accurate transcripts at their fingertips, they can easily capture quotes, analyze qualitative data, and fact-check information, enhancing the quality and credibility of their work. Academics and researchers, in particular, can benefit from seamless collaboration and sharing of research findings with colleagues.

Unlocking New Content Opportunities

Content creators and producers can harness the power of ScreenApp's tool to transcribe videos, podcasts, and live streams, enabling the creation of captions and subtitles. This not only enhances accessibility but also expands the reach of their content to broader audiences. Additionally, repurposing audio content into written formats becomes a breeze, unlocking new opportunities for engagement and discoverability.

Preserving Precious Moments

Finally, ScreenApp's Live Audio Transcriber Tool caters to personal use cases, allowing individuals to transcribe family stories, personal recordings, and cherished memories. Whether sharing transcripts with loved ones or preserving important conversations for future reference, this tool offers a convenient and efficient way to capture and document life's precious moments.

The addition of titles helps to organize the content and quickly communicate the key use cases to potential users, making it easier for them to identify the sections most relevant to their needs.

ScreenApp's Online Live Caption Tool FAQ

What is screenapp's live audio transcriber tool.

ScreenApp's Live Audio Transcriber Tool is a free online service that allows you to transcribe audio in real-time, converting spoken words into text instantly and accurately.

How does the live transcription feature work?

‍Our advanced speech recognition technology listens to the live audio input and converts it into text as the words are spoken, providing you with a real-time transcript without any delays.

Do I need to download or install any software to use the transcription tool?

No, ScreenApp's Live Audio Transcriber Tool is a web-based service that requires no downloads or installations. It can be accessed directly from your web browser.

What types of audio can I transcribe with this tool?

You can transcribe various types of audio content, including lectures, meetings, interviews, podcasts, videos, and more. The tool is versatile and suitable for a wide range of use cases.

Is there a limit on the duration of audio I can transcribe?

No, there are no limits on the duration of audio you can transcribe with ScreenApp's tool. You can transcribe audio recordings of any length.

Can I download or export the transcripts?

‍Yes, you can easily download the transcripts in various formats, such as text files or PDFs, for further editing, sharing, or archiving.

Does the tool support multiple languages?

‍Yes, ScreenApp's Live Audio Transcriber Tool supports transcription in multiple languages, ensuring broad accessibility and usefulness for a global audience.

Are there any advanced features available?

‍Absolutely! ScreenApp offers premium features like speaker diarization, which separates and labels multiple speakers in the transcript for enhanced organization and clarity.

How accurate is the transcription?

‍Our tool utilizes cutting-edge speech recognition technology to provide highly accurate transcriptions. However, accuracy may vary depending on factors like audio quality, background noise, and accents.

Is my audio data secure and private when using this tool?

Yes, ScreenApp prioritizes privacy and security. Your audio data is handled with robust security measures to ensure confidentiality and protection.

Still have questions?

Try it for yourself

More Audio Analyzers

Real-Time Transcription

Create a better user experience with the most accurate live transcription and subtitling

Instantly transcribe speech to text for live audio and video

Agora’s Real-Time Transcription provides accurate live transcription and subtitling services at a low cost.

Reduce cost and increase efficiency

Channel-based live transcription allows you to distribute live captions to all participants in channel while only paying for the duration of a channel—not the number of users. This approach is far more efficient and lower cost when compared to traditional client-side live transcription.

Get the most accurate results at scale

Cutting-edge AI ensures the highest accuracy even with overlapping speech, regional accents, and poor network conditions. Scale from one-to-one meetings to up to millions of participants with the same accuracy.

Integrate with ease

Simple API integration for a full solution supporting transcription from audio to text, live captioning, and cloud recording with closed captioning (CC) that works on any device. Extend with new features using the Restful API.

Features 

Live transcription for rtc.

Integrated with Agora’s voice and video service, live transcription and captions improve accessibility for your audience. Perfect for meetings, live streaming, lectures, interviews, live shopping, and more.

Channel-based cloud transcription

Cloud transcription service converts audio to text based on channel and distributes the text to all participants in this channel to show live closed captions (CC). Transcripts are saved to the cloud.

Transcribing and labeling simultaneous speakers

Easily label who said what—even with up to 3 simultaneous speakers. Separate transcription for each host ensures accurate voice transcription with multiple hosts.

Captioning for cloud recordings

Transcribe audio to text on video recordings to enable closed captions (CC) and review important discussion items in the transcript.

Multi-language support

Real-time transcription supports all major languages and dialects, and each channel can support audio to text transcription for up to two languages simultaneously.

Enterprise-grade security and compliance

Agora is ISO and SOC 2 certified and meets compliance standards for regional privacy laws and industry regulations, including GDPR, CCPA, and HIPAA.

Made for developers

Agora’s Real-Time Transcription platform-agnostic RESTful APIs make it easy to add highly accurate, cost-effective audio transcription capabilities to your app on any platform.

Transcribe speech to text for any live meetings or events

Securely transcribe and record real-time audio or video and organize recordings and transcripts to speed up workflows.

Education  

Give faculty and students real-time captions and notes for in-person and virtual lectures, classes or meetings.

Virtual Meetings

Provide real-time automated notes in meetings and conversations to keep everyone aligned in a remote work environment.

Social & Metaverse  

Eliminate communication barriers for people with different languages or disabilities.

Increase accessibility to reach a wider audience and improve discoverability for brands and hosts.  

Keep secure records of virtual appointments and patient questions with the most accurate speech to text software.

Events  

Empower your event with real-time, accurate notes, ensuring a more accessible, searchable, and engaging event experience.

Add live transcription to your real-time experience today

Get 1,000 minutes FREE 

Latest reviews

• Search resources
• OBS Studio Plugins

LocalVocal: Local Live Captions & Translation On-the-Go v0.3.2

• Author royshilkrot
• Creation date Aug 14, 2023

• Transcribe audio to text in real time in 100 languages
• Display captions on screen using text sources
• Send captions to a .txt or .srt file (to read by external sources or video playback) with and without aggregation option
• Sync'ed captions with OBS recording timestamps
• Send captions on a RTMP stream to e.g. YouTube, Twitch
• Bring your own Whisper model (any GGML)
• Translate captions in real time to major languages (both Whisper built-in translation as well as NMT models with CTranslate2 )
• CUDA, OpenCL, Apple Arm64, AVX & SSE acceleration support
• More robust built-in translation options
• Additional output options: .vtt, .ssa, .sub, etc.
• Speaker diarization (detecting speakers in a multi-person audio stream)
• Background Removal removes background from webcam without a green screen.
• Detect will detect and track >80 types of objects in real-time inside OBS
• URL/API Source that allows fetching live data from an API and displaying it in OBS.

More resources from royshilkrot

Share this resource

Latest updates, v0.3.2 improvements all around caption presentation, logs and bugfixes, v0.3.1 - more models, fix timestamps, v0.3.0 big release far better experience, more translation, bugs squashed.

• 5.00 star(s)
• Jun 12, 2024
• Version: v0.3.1
• Feb 25, 2024
• Version: v0.1.0
• Dec 18, 2023
• Version: v0.0.7

• Sep 18, 2023
• Version: v0.0.2
• This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register. By continuing to use this site, you are consenting to our use of cookies. Accept Learn more…

Speech-to-Text live streaming for live captions, powered by the world's leading speech recognition API

Rev AI's live streaming Speech-to-Text engine powers real-time captioning for your business. Our captions ensure that live talks and trainings are accessible and can be archived for future use.

Get your transcription in real-time with Rev AI's streaming API.

Rev AI serves your industry

Our single English model supports all major English accents from around the world, eliminating the need to pay extra and switch models for different speakers and conversations. We provide you with the best English results out-of-the-box, regardless of who is speaking. More languages coming soon.

Transcend barriers of communication with Rev AI

Build “real” real-time transcription software.

On-device streaming speech-to-text with cloud-level accuracy without cloud latency

What is Cheetah Streaming Speech-to-Text?

Cheetah Streaming Speech-to-Text is software that automatically transcribes voice data in real time without network delay or accuracy compromises.

Cheetah Streaming Speech-to-Text processes voice data locally, enabling live transcription on-device, mobile, web browsers, on-premise, or cloud.

Build with cross-platform transcription SDKs

Why cheetah streaming speech-to-text.

Real-time transcription APIs send voice data to the vendor’s cloud, making them vulnerable to latency, congestion, outages, and throttling.

Cheetah Streaming Speech-to-Text processes voice data when and where received, resulting in a guaranteed real-time transcription experience without unpredictable delays.

Less is more!

Record, upload, and process voice data, then download text and show the transcript.

All performance…

Cheetah Streaming Speech-to-Text brings cloud transcription API accuracy to any platform…

… in “real” real time by overcoming inherent cloud limitations with on-device voice recognition.

Evaluate the accuracy of transcription software transparently

Boost the accuracy of cheetah speech-to-text with customization.

Deploy Cheetah Streaming Speech-to-Text on any platform

Generate real-time transcripts with no network delays, ensure voice data and transcript privacy and security, cheetah streaming speech-to-text.

Does Cheetah Streaming Speech-to-Text sound too good to be true? See for yourself!

• Pre-trained transcription models
• Custom vocabulary
• Keyword boosting
• Intuitive SDKs
• Trucasing and Punctuation

More from Picovoice

Ai voice assistant for ios powered by local llm, ai voice assistant for android powered by local llm, local llm-powered voice assistant for web browsers, on-device llm-powered voice assistant in python, spanish speech-to-text with python, javascript speech recognition, what is a real-time transcription engine.

Real-time transcription, also known as real-time speech-to-text, streaming transcription, streaming speech-to-text, live transcription, or live speech-to-text, refers to the technology and tools that convert audio streams to text synchronously with audio generation.

How does on-device real-time transcription differ from cloud-based real-time transcription APIs?

Cloud-based real-time transcription APIs record and send voice data to vendor servers where the transcription engine resides to convert voice into text. On-device real-time transcription brings the transcription engine where voice data is, offering guaranteed real-time experience by eliminating unpredictable delays.

What are the benefits of on-device real-time transcription over cloud-based real-time transcription?

Cloud-based real-time transcription converts voice data into text with delay due to network latency and connectivity issues. On-device real-time transcription eliminates these inherent latency and reliability limitations by processing voice data on the device without sending it to a 3rd party cloud. For time-sensitive applications, such as agent assistance, medical dictation , or meeting transcription, delays affect the experience and productivity. A recent study on delays in virtual communication depicts internet lag as a wrench in mental gears .

Can I use Cheetah Streaming Speech-to-Text in the cloud?

Yes. You can run Cheetah Streaming Speech-to-Text in the cloud, whether private, public, or hybrid. Picovoice on-device voice recognition technology allows enterprises to decide where to run the transcription engine instead of making the Picovoice cloud mandatory for voice processing.

What are the key metrics for evaluating real-time transcription engines?

Key metrics for evaluating real-time transcription engines are latency, reliability & resiliency, accuracy, availability of features, the total cost of ownership, and data privacy and governance. Each metric may have different weights in different projects of the same company.

Which platforms does Cheetah Streaming Speech-to-Text support?

• Desktop and Servers: Linux , macOS , and Windows
• Web Browsers: Chrome , Safari , Edge , and Firefox
• Mobile Devices: Android and iOS
• Single Board Computers: Raspberry Pi and NVIDIA Jetson

Which languages does Cheetah Streaming Speech-to-Text support?

Cheetah Streaming Speech-to-Text only supports English for now.

What should I do to request Cheetah Streaming Speech-to-Text to support other languages?

Reach out to Picovoice Sales to tell us about your commercial endeavor.

How do I get technical support for Cheetah Streaming Speech-to-Text?

Picovoice docs , blog , Medium posts , and GitHub are great resources to learn about voice AI, Picovoice technology, and how to start building transcription products. You can report bugs and issues on GitHub. If you need help with developing your product, you can purchase the optional Support Add-on or upgrade your account to the Developer Plan .

How can I get informed about updates and upgrades?

Version changes appear in the Picovoice Newsletter and LinkedIn . Subscribing to GitHub is the best way to get notified of patch releases. If you enjoy building with Cheetah Streaming Speech-to-Text, show it by giving a GitHub star!

Transcribe App and Online Editor

Your personal assistant for note taking and transcribing. our voice transcription service saves you time and helps you focus on what’s important..

Automatic transcription

Transcribe is your AI-powered speech-to-text service. Use the Transcribe app and online editor to automatically generate notes from meetings, interviews, videos and more.

More than 120 languages

Turn audio and video into searchable, editable and shareable content in more than 120 languages.

Spanish (Spain)

Spanish (Mexican)

Spanish (Colombian)

Traditional Chinese

Variety of formats

Import files from any app or cloud storage system. Supported formats include mp3, m4a, wav, m4v, mp4, mov and avi.

Document export

Export transcribed text into a document with timestamps and polish it there. Supported formats include PDF and Microsoft Word.

Zoom integration

Record your Zoom calls and get meeting notes almost instantly.

Voice recorder

Record and review conversations in real time with our live transcription service.

Dim the lights when you work late into the night.

Collaboration tools

Collaborate with your colleagues by exporting voice notes or using Teams feature.

Bonus 5 hours of transcription time

Additional time credits every month.

Additional export formats

Export to TXT, PDF, DOCX, SRT and JPG.

Cloud storage

Up to 500 files of speech recording can be backed up in the cloud.

Synchronization

Access your documents from any device (iPhone, iPad, MacOS or a web browser).

Edit on your phone, PC or Mac

Proofread and polish the transcription on whichever device you prefer.

Priority support

Speedier replies and help when you need it.

Bonus 30 hours of transcription time

Ability to create teams for collaboration (up to 5 teams).

Up to 1 000 audio files with infinite storage time.

For podcasters

Transcribe podcasts into written notes.

For business

Get meeting notes in an instant.

For journalists

Transcribe interviews to get news out fast.

For academics

Save time on your academic research.

For students

Transcribe lectures and seminars.

What our users are saying

I’m a freelance writer who uses the Voice Memo app when conducting interviews. It would take me HOURS to transcribe what was recorded. And that wasted my time when I could have been writing the article. Transcribe has now freed up that time.

I am disabled and I’ve been looking for this exact technology for at least two years because I can’t type anymore. A lot of these transcriptions don’t work, but this one does. I’ve probably done 60 hours of transcribing audio memos checks and with with very few exceptions it was Word for Word perfect. And when you didn’t get the word right it was because I was mumbling, or what have you.

This converted my rambling voice memos directly into text for use in a word document. My audio quality was low: I recorded with my iPhone in my lap while driving on the highway so there is lots of background noise. Still, the imperfections in text are all from me stammering. Actually, the app cut out lots of ums and repeated words improving what I said. It still requires editing and correcting - mostly formatting - but really couldnt be improved much at all. This is mature technology. Also, the software interface is top notch, like google or even better.

Time-saver and amazing results! Thanks a lot for this help! I often have to work with texts in German, English, Italian.

Just used this app to transcribe a 24 minute interview (on Apple Voice Memos) with my dad, about our family history. Using this app vs. transcribing it myself has literally saved me hours. The transcription was good enough that all I will need to do is clean up a few minor “misreads”, and I can present a written version of this interview to my dad as a gift for Christmas. Thanks for a great app!

I am very pleased with this app. I use it primarily to transcribe short information videos. I purchase time in one hour increments which is suitable for my needs.

Experts talk about Transcribe

Best voice-to-text apps.

Voice-to-text apps can be very useful for busy professionals. If you're always on the go or you think faster than you can write, these special programs can increase efficiency and store your recordings safe and sound via the cloud.

The 6 Best Dictation Apps for iPhone

If the iPhone's built-in dictation feature doesn't cut it for you, here are a few good dictation apps for you.

10 iPhone Speech-to-Text Apps 2021

If you don't want to type long texts yourself, a transcription service will be the best solution for you.

Speech to Text - Voice Typing & Transcription

Take notes with your voice for free, or automatically transcribe audio & video recordings. secure, accurate & blazing fast..

~ Proudly serving millions of users since 2015 ~

I need to >

Dictate Notes

Start taking notes, on our online voice-enabled notepad right away, for free.

Transcribe Recordings

Automatically transcribe (as well as summarize & translate) audios & videos. Upload files from your device or link to an online resource (Drive, YouTube, TikTok or other). Export to text, docx, video subtitles & more.

Speechnotes is a reliable and secure web-based speech-to-text tool that enables you to quickly and accurately transcribe your audio and video recordings, as well as dictate your notes instead of typing, saving you time and effort. With features like voice commands for punctuation and formatting, automatic capitalization, and easy import/export options, Speechnotes provides an efficient and user-friendly dictation and transcription experience. Proudly serving millions of users since 2015, Speechnotes is the go-to tool for anyone who needs fast, accurate & private transcription. Our Portfolio of Complementary Speech-To-Text Tools Includes:

Voice typing - Chrome extension

Dictate instead of typing on any form & text-box across the web. Including on Gmail, and more.

Transcription API & webhooks

Speechnotes' API enables you to send us files via standard POST requests, and get the transcription results sent directly to your server.

Zapier integration

Combine the power of automatic transcriptions with Zapier's automatic processes. Serverless & codeless automation! Connect with your CRM, phone calls, Docs, email & more.

Android Speechnotes app

Speechnotes' notepad for Android, for notes taking on your mobile, battle tested with more than 5Million downloads. Rated 4.3+ ⭐

iOS TextHear app

TextHear for iOS, works great on iPhones, iPads & Macs. Designed specifically to help people with hearing impairment participate in conversations. Please note, this is a sister app - so it has its own pricing plan.

Audio & video converting tools

Tools developed for fast - batch conversions of audio files from one type to another and extracting audio only from videos for minimizing uploads.

Our Sister Apps for Text-To-Speech & Live Captioning

Complementary to Speechnotes

Reads out loud texts, files & web pages

Reads out loud texts, PDFs, e-books & websites for free

Speechlogger

Live Captioning & Translation

Live captions & translations for online meetings, webinars, and conferences.

Need Human Transcription? We Can Offer a 10% Discount Coupon

We do not provide human transcription services ourselves, but, we partnered with a UK company that does. Learn more on human transcription and the 10% discount .

Dictation Notepad

Start taking notes with your voice for free

Speech to Text online notepad. Professional, accurate & free speech recognizing text editor. Distraction-free, fast, easy to use web app for dictation & typing.

Speechnotes is a powerful speech-enabled online notepad, designed to empower your ideas by implementing a clean & efficient design, so you can focus on your thoughts. We strive to provide the best online dictation tool by engaging cutting-edge speech-recognition technology for the most accurate results technology can achieve today, together with incorporating built-in tools (automatic or manual) to increase users' efficiency, productivity and comfort. Works entirely online in your Chrome browser. No download, no install and even no registration needed, so you can start working right away.

Speechnotes is especially designed to provide you a distraction-free environment. Every note, starts with a new clear white paper, so to stimulate your mind with a clean fresh start. All other elements but the text itself are out of sight by fading out, so you can concentrate on the most important part - your own creativity. In addition to that, speaking instead of typing, enables you to think and speak it out fluently, uninterrupted, which again encourages creative, clear thinking. Fonts and colors all over the app were designed to be sharp and have excellent legibility characteristics.

Example use cases

• Voice typing
• Writing notes, thoughts
• Medical forms - dictate
• Transcribers (listen and dictate)

Transcription Service

Start transcribing

Fast turnaround - results within minutes. Includes timestamps, auto punctuation and subtitles at unbeatable price. Protects your privacy: no human in the loop, and (unlike many other vendors) we do NOT keep your audio. Pay per use, no recurring payments. Upload your files or transcribe directly from Google Drive, YouTube or any other online source. Simple. No download or install. Just send us the file and get the results in minutes.

• Transcribe interviews
• Captions for Youtubes & movies
• Auto-transcribe phone calls or voice messages
• Students - transcribe lectures
• Podcasters - enlarge your audience by turning your podcasts into textual content
• Text-index entire audio archives

Key Advantages

Speechnotes is powered by the leading most accurate speech recognition AI engines by Google & Microsoft. We always check - and make sure we still use the best. Accuracy in English is very good and can easily reach 95% accuracy for good quality dictation or recording.

Lightweight & fast

Both Speechnotes dictation & transcription are lightweight-online no install, work out of the box anywhere you are. Dictation works in real time. Transcription will get you results in a matter of minutes.

Super Private & Secure!

Super private - no human handles, sees or listens to your recordings! In addition, we take great measures to protect your privacy. For example, for transcribing your recordings - we pay Google's speech to text engines extra - just so they do not keep your audio for their own research purposes.

Health advantages

Typing may result in different types of Computer Related Repetitive Strain Injuries (RSI). Voice typing is one of the main recommended ways to minimize these risks, as it enables you to sit back comfortably, freeing your arms, hands, shoulders and back altogether.

Saves you time

Need to transcribe a recording? If it's an hour long, transcribing it yourself will take you about 6! hours of work. If you send it to a transcriber - you will get it back in days! Upload it to Speechnotes - it will take you less than a minute, and you will get the results in about 20 minutes to your email.

Saves you money

Speechnotes dictation notepad is completely free - with ads - or a small fee to get it ad-free. Speechnotes transcription is only $0.1/minute, which is X10 times cheaper than a human transcriber! We offer the best deal on the market - whether it's the free dictation notepad ot the pay-as-you-go transcription service.

Dictation - Free

• Online dictation notepad
• Voice typing Chrome extension

Dictation - Premium

• Premium online dictation notepad
• Premium voice typing Chrome extension
• Support from the development team

Transcription

$0.1 /minute.

• Pay as you go - no subscription
• Audio & video recordings
• Speaker diarization in English
• Generate captions .srt files
• REST API, webhooks & Zapier integration

Compare plans

Privacy Policy

We at Speechnotes, Speechlogger, TextHear, Speechkeys value your privacy, and that's why we do not store anything you say or type or in fact any other data about you - unless it is solely needed for the purpose of your operation. We don't share it with 3rd parties, other than Google / Microsoft for the speech-to-text engine.

Privacy - how are the recordings and results handled?

- transcription service.

Our transcription service is probably the most private and secure transcription service available.

• HIPAA compliant.
• No human in the loop. No passing your recording between PCs, emails, employees, etc.
• Secure encrypted communications (https) with and between our servers.
• Recordings are automatically deleted from our servers as soon as the transcription is done.
• Our contract with Google / Microsoft (our speech engines providers) prohibits them from keeping any audio or results.
• Transcription results are securely kept on our secure database. Only you have access to them - only if you sign in (or provide your secret credentials through the API)
• You may choose to delete the transcription results - once you do - no copy remains on our servers.

- Dictation notepad & extension

For dictation, the recording & recognition - is delegated to and done by the browser (Chrome / Edge) or operating system (Android). So, we never even have access to the recorded audio, and Edge's / Chrome's / Android's (depending the one you use) privacy policy apply here.

The results of the dictation are saved locally on your machine - via the browser's / app's local storage. It never gets to our servers. So, as long as your device is private - your notes are private.

Payments method privacy

The whole payments process is delegated to PayPal / Stripe / Google Pay / Play Store / App Store and secured by these providers. We never receive any of your credit card information.

More generic notes regarding our site, cookies, analytics, ads, etc.

• We may use Google Analytics on our site - which is a generic tool to track usage statistics.
• We use cookies - which means we save data on your browser to send to our servers when needed. This is used for instance to sign you in, and then keep you signed in.
• For the dictation tool - we use your browser's local storage to store your notes, so you can access them later.
• Non premium dictation tool serves ads by Google. Users may opt out of personalized advertising by visiting Ads Settings . Alternatively, users can opt out of a third-party vendor's use of cookies for personalized advertising by visiting https://youradchoices.com/
• In case you would like to upload files to Google Drive directly from Speechnotes - we'll ask for your permission to do so. We will use that permission for that purpose only - syncing your speech-notes to your Google Drive, per your request.

What Is a Live Streaming Speech Recognition API & Why Use It?

Rev › Blog › Speech to Text Technology › What Is a Live Streaming Speech Recognition API & Why Use It?

Standard speech recognition services are perfect when you need to caption occasional videos or audio recordings. But for some needs, access to the underlying technology that powers these services can take your business further. This is where a speech recognition API is valuable.

A live streaming speech recognition API allows you to hook your applications up to an automatic speech recognition (ASR) engine. The API ( Application Programming Interface ) acts as an intermediary between the application and a remote server with an ASR. For example, if you build the Rev API into your website, your website can communicate with Rev’s speech-to-text engine via the API. A customer could transcribe their voice with a click.

Setting up an API requires coding knowledge. But the end-user should have a no-rivets experience. The end-user might be a customer accessing the website where the API is embedded or an employee using a company tool.

Common uses of live streaming speech recognition APIs include word processing, mass transcription of call center conversations, and the real-time captioning of live events.

How does a Live Streaming Speech Recognition API work?

A live streaming speech recognition API needs to be founded on a speech engine. In the case of Rev’s API, this engine is an industry-leading speech recognition AI (artificial intelligence). Unlike other leading engines, Rev has developed its tool with a human-generated training set rather than statistical analysis—machine learning with a conscientious human touch.

You can build Rev’s speech recognition API into your apps using a software development kit (SDK). It is possible to do this using various coding languages, including Python, JavaScript, and Go. When you send a transcription request via the Rev API, Rev’s software interprets the spoken word in the audio stream by comparing the fundamentals to our extensive library of words, phrases, accents, and sentences.

Rev offers two APIs:

• An asynchronous API for pre-recorded audio and video files. It returns a transcription or captions of hour-long files in under a minute.
• A streaming API for real-time captioning of live audio/video, keyword-monitoring, and implementing actions based on specified trigger words.

The asynchronous API uses REST (Representational State Transfer). And the streaming API uses RTMP ( Real-Time Messaging Protocol ).

We offer output in .json or .txt format. Rev’s API comes with software development kits, full documentation, and expert support.

How Accurate is It?

AI transcription is not yet as accurate as a professional human service , which may achieve 99% accuracy or more. But speech-to-text AI can achieve accuracy of 85% and higher. (On high-quality audio with native English speakers, Rev AI’s results are in the low-mid 90s ). Human transcription is still preferable where near-perfect accuracy is essential. But if speed and cost at scale are priorities, the best AI now delivers excellent results.

The big tech companies use statistical analysis to train their models. But Rev’s machine learning is founded on manual training. Rev works around the clock with a team of 50,000 human professionals to transcribe and caption the spoken word. We trained the Rev AI with ten years of human-sourced data. Our developers carefully collected and edited it rather than simply harvesting masses of audio, as in the case of Siri and Alexa. Indeed, ASR is the core of what we do. The result? A live streaming speech recognition API that outperforms tech’s biggest names.

Rev performed Word Error Rate (WER) tests on our own automated transcript service, the Google Cloud speech API, and those of Amazon and Microsoft. We outperformed them all. (You can check our results and methodology here ). Not all speech engines can label different speakers in a room, but Rev does that, too.

Another advantage of Rev’s API is that you can boost accuracy by sharing unusual names and terminology before using it.

Why Use a Live Streaming Speech Recognition API?

Live streaming speech recognition is a great asset for individuals and businesses. Developers utilize the power of a purpose-built speech engine by integrating it into their companies’ platforms and services.

Making live videos, conferences, and webinars accessible is ethical. In many cases, it’s a legal requirement. A real-time speech-to-text API delivers instant captioning and transcription to guarantee that everyone is included. Of course, your transcribed speech remains available afterward as a searchable archive.

Rev has trained our API on major English accents from around the world. This simplifies your transcription workflow as you don’t need to organize or pay for extra services.

Many businesses where the spoken word is central to service can benefit from speech-to-voice tech. And for many of these businesses, an AI-powered speech recognition API is the most affordable and efficient choice.

Here are some use cases where a streaming API could be a valuable asset:

• Facilitate the monitoring of support call quality.
• Refer to transcripts for training purposes or auditing.
• Train an interactive voice response (IVR) system to stand in for agents.
• Integrate voice typing capabilities or hands-free voice commands into your software.
• Create a searchable user inquiry history for your virtual assistant to support development.
• Deliver real-time live captioning of events in-venue.
• Improve accessibility for participants attending online.
• Share transcriptions with participants after the event.
• Provide timestamped lecture transcriptions to students rather than manually-prepared notes.
• Live caption online lectures; explore translation options for ESL students.
• Automate captioning quickly and at scale.
• Offer transcriptions. This can boost discoverability, accessibility, and usability.
• Dictate and automatically transcribe electronic health records (EHRs) after visits.

If these use cases sound advantageous to you, you can access the Rev.ai API to get started with real-time captions and transcription. Prices start at $0.035 per audio minute and get lower as volumes increase.

And if you’re not sure how live streaming speech recognition API might work for you – or whether it’s the right speech-to-text option for your business – speak to us , and we’ll help you find the right solution for your needs.

Related Content

Latest article.

Extract Topics from Transcribed Speech with Node.js

Most popular.

What Are the Advantages of Artificial Intelligence?

Featured article.

What is ASR? The Guide to Automatic Speech Recognition Technology

Everybody’s favorite speech-to-text blog.

We combine AI and a huge community of freelancers to make speech-to-text greatness every day. Wanna hear more about it?

• About AssemblyAI

10 Ways Streaming Speech-to-Text (Live Transcription) is Being Used Today

Learn 10 ways Streaming Speech-to-Text (live transcription) is being used today across industries.

Featured writer

Streaming Speech-to-Text technology (also known as live transcription) converts real-time audio streams into accurate text. From live sporting events to conference calls, live transcription makes interactions more engaging and accessible for everyone.

Industries including financial services, health care, customer support, and market research are using Streaming Speech-to-Text to drive engagement, improve accessibility, and generate immediate insights.

Below, we'll walk you through a handful of live transcription use cases we're seeing across industries. But first, let's quickly recap live transcription and why it matters.

What Is Live Transcription?

Live transcription is the process of converting spoken language into written text in real-time. Traditionally, humans would be responsible for listening to live content and typing it out (usually at a delay) as it happens. Now, artificial intelligence and machine learning empower speech-to-text solutions to automatically transcribe (and even translate) content in real-time with minimal human intervention.

Live transcription relies on a combination of advanced speech recognition and natural language processing. Here's a high-level overview of the process:

• Audio Capture: The audio input is captured through microphones or other recording devices.
• Speech Recognition: The audio is processed by a speech recognition solution that converts the spoken words into text.
• Real-Time Display: The transcribed text is displayed in real-time, with minimal latency, to let viewers follow along as the speech happens.

Live Transcription vs. Post-Event Transcription

While live and post-event transcription serve the same purposes, they do it in different ways:

• Timing: Live transcription happens in real-time during the event, while post-event transcription is done after the event has concluded.
• Accuracy: Post-event transcription can be more accurate since it allows for editing and correction, whereas live transcription prioritizes speed and may include minor errors.
• Usage: Live transcription is ideal for accessibility during live events, webinars, and meetings, providing immediate text for participants. Post-event transcription is used to create detailed, polished records for future reference, sharing, analytics, and archiving.

What Are the Benefits of Live Transcription?

While the end result of live transcription is simply written text, there's a lot you can do with a transcription versus only the audio recording. From improved accessibility to searchability and analytics, Streaming Speech-to-Text can help in several ways:

• Improved Accessibility: Makes spoken content accessible to individuals who are deaf or hard of hearing.
• Higher Engagement: Helps participants follow along (especially in noisy environments or speakers with strong accents).
• Better Record-Keeping: Offers an immediate and accurate record of spoken content—essential for meeting minutes, legal records, or educational notes.
• Greater Searchability: Lets users find specific information or topics for reviewing content, preparing summaries, and extracting key points
• Language Translation: Can be paired with translation services to provide real-time subtitles in different languages.
• Regulatory Compliance: Provides a verifiable record of interactions for accurate documentation.
• Analytics: Empowers advanced analytics by providing structured data, ready to be analyzed to extract insights, identify trends, and measure performance.

10 Real-World Live Transcription Use Cases

Live transcription is becoming faster, more reliable, and more accurate—and that's expanding the list of practical use cases. Let's take a look at how organizations are leveraging live transcription today. 

1. Live Broadcasts

Live transcription in broadcasts creates on-screen subtitles or captions for viewers to follow. You'll see this for everything from live sporting events and concerts to social media live streams and even gaming streams.

During the event, these live transcriptions make the content more accessible and easy to follow (especially for those who prefer to read content). Following the live event, the transcribed content helps create searchable archives.

2. Virtual Meetings and Conferences

Everything from team meetings and company all-hands to virtual conferences or hybrid events can benefit from live transcription. This could be creating real-time captions to follow along with or even on-display transcriptions on a digital screen during an in-person event.

You can even pair your transcription services with translation tools to provide real-time subtitles in multiple languages. Participants can focus more on the discussion rather than taking notes—because high-quality streaming speech-to-text models are part of a broader AI platform that can distinguish between speakers, summarize meetings, and even highlight takeaways and action items.

3. Customer Service and Support

Live transcription supports customer service agents and callers by providing real-time text of customer interactions. This allows for immediate analysis, documentation, and follow-up—it can even alert managers and higher-ups if they might need to hop on a call to help or intervene.

The live transcriptions can be stored for documentation, reference, or analysis following the interactions. You can use these learnings to power agent training and learn which strategies work (or don't).

4. Education and Online Learning

Schools, colleges, and online learning programs can use live transcription services to provide accurate and timely notes. It can help with lectures, seminars, interactive sessions, and workshops.

Students can focus on understanding and participating in the lesson rather than frantically taking notes. Transcripts can be reviewed later for better retention. Transcription can also be integrated with more interactive tools to let students highlight, comment, and discuss specific parts of a lesson.

5. Legal Proceedings

Live transcription in legal proceedings provides real-time text conversion of courtroom discussions, depositions, and other legal activities. This provides accurate and immediate records of documentation, legal accuracy, and accountability.

Layers, judges, and jurors can use live transcription services to better follow conversations in real time. Some attorneys can speak quickly—having a transcription helps everyone stay on the same page. Journalists can also use live transcriptions to get instant access to accurate quotes and proceedings to use in timely articles without waiting for official post-event documentation.

6. Health care and Telemedicine

Healthcare organizations and telemedicine can use live transcription to convert spoken medical consultations, patient interactions, and clinical discussions into real-time text. This is especially important for increasingly prevalent virtual care when sound quality and accents could lead to misunderstandings or miscommunication.

Creating accurate, real-time documentation of medical consultations reduces the risk of errors in patient records. It also gives all patients instant access to important medical information.

Administrative roles can also use live transcription to streamline transcribing medical conversations, allowing them to focus more on patient care and less on scribbling notes.

7. Financial Services

The financial services industry can use live transcription for client meetings, investment briefings, and earnings calls. This improves transparency, compliance, and accessibility.

These live transcriptions provide accurate records for immediate review and analysis. It keeps all interactions documented accurately for searchable records and potential auditing.

8. Government and Public Sector

Government organizations can use live transcription for in-person meetings, public hearings, press conferences, town halls, and other official events. This makes all the proceedings more accessible to your community and creates accurate, searchable records for documentation and historical archiving.

9. Market Research and Focus Groups

Market research organizations use live transcription for real-time discussions, interviews, and focus groups. Having instant access to these transcriptions allows for immediate consumer insights, trends, and preferences analysis. It also lets you ask more relevant follow-up questions rather than collecting and gleaning all the insights post-discussion when your group is no longer accessible.

Automated transcription reduces human error and also lets your team stay engaged in the conversation rather than note-taking. Following the interviews, researchers can quickly compile large volumes of data from multiple focus groups for more extensive analysis.

10. AI-Powered Live Assistants

AI-powered live assistants change how we interact with technology and access information in real-time. They combine live transcription and natural language processing with text-to-speech systems to provide immediate, accurate responses to user inputs and questions.

For example, during live events or meetings, AI-powered live assistants can transcribe spoken words into text and then process that text to generate relevant answers, summaries, or follow-up questions.

In customer service, AI-powered live assistants can handle multiple queries simultaneously to provide real-time support and free up human agents for more complex tasks. The integration of live transcription with AI allows these assistants to understand context, detect sentiment, and offer personalized interactions.

Build Live Transcription Solutions with an AI Partner

Integrating live transcription into your products, services, events, and experiences doesn't need to require heavy upfront investments or vast technical resources—you just need the right partner.

Look for advanced speech-to-text solutions that provide unmatched accuracy, scalability, and reliability:

• High Accuracy: Achieve near-human level transcription accuracy with state-of-the-art models (even with poor audio conditions like noisy backgrounds).
• Scalability: Handle large volumes of audio and video data seamlessly, whether it's for small teams or large enterprises.
• User-Friendly API: An API that is simple to integrate, letting you quickly start transcribing and analyzing audio data.

Test our API in minutes in our Playground and see how easy it is to transcribe and analyze audio in real time. Ready to start building? Sign up for a free account to access speech-to-text and audio intelligence models to transcribe up to 100 hours of audio the free Speech-to-Text (and more) plan.

Popular posts

AI trends in 2024: Graph Neural Networks

Developer Educator at AssemblyAI

AI for Universal Audio Understanding: Qwen-Audio Explained

Combining Speech Recognition and Diarization in one model

How DALL-E 2 Actually Works

A new standard for AI powered live captions

Add flawless closed captions to your live stream through automatic speech-to-text conversion.

Our AI powered captioning solution is easy to use, reliable and efficient. Its unique speech-to-text technology, with optional support for human real-time correction, makes your captions more accurate and readable than ever.

Unique speech-to-text technology

Our technology for auto-generating closed captions leverages the latency that comes with the HTTP Live Streaming protocol. By slightly increasing it, we achieve a triple goal:

• Longer audio streams can be sent to the Automatic Speech Recognition (ASR) engine. This allows the ASR engine to better interpret the words and construct correct phrases and sentences. This increases the accuracy of the conversion.
• Optionally, a human editor can make real-time corrections to the automatically generated captions, before they are translated and shown in the live stream.
• Clevercast has slightly more time to process the ASR output. This allows us to improve the readability of the captions and makes them easier to understand .

Most accurate live captions available

For an indication of the difference in accuracy and readability with other platforms, we recorded the same live stream with auto-generated captions in Clevercast, YouTube and Vimeo. All recordings are unedited.

The live stream featured a number of different speakers, each with their own speech pattern and accent.

Note that Clevercast features to improve caption accuracy, such as keyword vocabularies and real-time correction, were NOT used during this test. All captions were generated fully automatically in real-time, without human intervention.

If you want to assess the quality of our live closed captions firsthand, don’t hesitate to request a trial account .

Above are unedited recordings of the same live stream with auto-generated captions in Clevercast, YouTube and Vimeo. The demo uses excerpts from the following videos available June 20, 2023 under a CC-BY 4.0 license:

Paywall: The Business of Scholarship by Jason Schmitt Will saving poor children lead to overpopulation? Free material from WWW.GAPMINDER.ORG

Real-time correction for 100% accuracy

Even though the accuracy of speech-to-text conversion is already very high, some live streams require perfection. That’s why Clevercast offers a real-time correction interface .

The cloud interface lets you edit the AI generated captions in real-time , just before they are sent to the live stream (and translated into other languages). It lets you change words and move them to different lines for improved readibility.

Making these corrections is a simple task that requires no experience or training . Our intuitive interface allows anyone to edit the captions in a browser with mouse and keyboard.

Intelligent caption rendering in the player

Because of the increased latency, Clevercast can add the captions to the live stream in an intelligent manner. This allows Clevercast player to show (partial) sentences, rather than separate words . This makes the closed captions easier to read and understand.

Viewers, anywhere in the world, can watch the live stream and select their preferred caption language in our video player. Our customizable HTML5 player can be easily embedded into any device and platform. Just copy the embed code from Clevercast.

Alternatively, you can choose to display the rolling text in a separate widget . This widget also allows your viewers to change their preferred language.

Live AI translation to other languages

Clevercast can automatically translate closed captions in real-time and make the additional languages available in the live stream.

The accuracy of the translations mostly depends on the quality of the source captions. With an accurate source, all extra languages – even unpopular ones – will be translated with an 99.9+% accuracy . Note that when using our correction interface, the corrected captions will be used as the source for translation.

Alternatively, you can also use a professional captioner for the source language, combined with AI translation for the extra languages.

Cloud recording and Video on-Demand

Clevercast makes a cloud recording of the multilingual live stream, which can be downloaded. All caption languages can be downloaded as WebVTT files . This allows you to upload them to YouTube or social media channels for on-demand viewing.

You can also convert the cloud recording of your live stream to Video on-Demand (VoD). Our VoD player with all closed captions can be added to your site or platform by copying the embed code for your event.

Let us assist you

If you have no experience with automatically generated closed captions and are not sure whether it is the right choice for your event, don’t hesitate to contact us .

We can help you review your options and provide the necessary tips. If desired, we can offer professional correctors for your event, communicate with them, provide them with all the relevant documentation and monitor your live stream.

Get Started Now

Start live streaming today with a solution of choice. No credit card required.

Or contact us for more info.

Written by StreamYard

Top Video Transcription Tools For Live Streamers

Are you looking for the best video transcription tool for live streamers?

You're not alone — content creators, video marketers, and brands can immensely benefit from video transcription.

With the right solution, you can reduce your video transcription turnaround time, get more accurate results and reach a wider audience.

Let's take a look at some of our favorite tools to help speed up video transcription.

What Is A Video Transcription Tool?

Remember the feeling of searching a song's lyrics just because you couldn't get a word right? Well, that's how video transcriptions work.

A video transcript is a video's entire audio content available to you in written form. And a video transcription tool is software or a solution that transcribes a video. Using a video transcription tool means you no longer have to pause and rewind video files to transcribe them manually.

While a great tool makes the video transcription job quick and easy, it has more benefits. Let's check them out.

Why Use A Video Transcription Tool?

You can hire a freelancer or a transcription agency to transcribe videos. So, why use a tool?

Many video transcription tools help automate the transcription process, which can save a lot of time. It's also much less expensive than outsourcing the task to a freelancer or agency, which will typically charge you per minute. With most of the tools available free of cost and AI supporting their accuracy claims, converting your video content into written text is like using a magic wand.

So with a transcription tool, you can quickly and easily generate transcripts, saving your money, time and effort.

Then, when you have the transcripts ready, you can add them to the video for improved accessibility and search engine visibility or repurpose them into podcasts , blogs, summaries, courses, and even emails. In short, a transcription tool also helps you create stellar experiences that your audiences can learn from even when your live video is over.

Here's a video on repurposing you must check out to learn how to create a content engine using your live videos:

Things To Consider While Choosing A Video Transcription Tool

You've likely experienced disappointment using an online tool before.

Or found it too difficult to understand, thanks to a seemingly endless learning curve.

These may be some common pain points users face while using a digital solution. If you're worried a video transcription tool will have the same fate, we're here to help.

You can avoid falling prey to these trivial issues by considering the following points while choosing transcription software:

Like with any software, video transcription software is also built with different use cases in mind. For example, one may be great at generating captions, and another may be good for transcribing a meeting with various speakers. So, pick a tool that suits your purpose, and you'll most likely end up with more accurate results.

Turnaround Time

A video transcription tool's responsiveness opens the door for quick results. Some of these tools can transcribe videos in a couple of minutes. This empowers live streamers to quickly add transcripts to the saved replays as they cross-promote them or even repurpose them.

Creators should know what to expect when using automated software. Remember, the accuracy of online transcription tools is fair game. Unfortunately, one has to trade accuracy with turnaround time more often than not. While manual transcription services are exceedingly accurate yet time-consuming, online tools stand close to the 80% accuracy mark (most of the time). So, choosing software that picks up speech correctly should be a priority.

Keep in mind that video transcription tools analyze your voice, so if your speech isn't clear, it may miss some words; however, they get you most of the way there. Some tools even listen to and analyze a video and use artificial intelligence to improve wording for future ones.

Adding on to the previous point, your chosen video transcription software should be able to support multiple speakers and accents. These features and the tool's ability to decipher speech add to the efficiency. Some transcription tools also come with built-in background noise reduction for better results. And some even support translation with foreign subtitles, giving the best form and power live streamers need in an online video transcription tool.

Keep in mind that you can use a video transcription tool for more than just live streaming. They're great for creating captions for your videos on YouTube or Facebook.

Mobile Compatibility

Live streamers on the go would need a transcription tool that can be accessed on mobile devices. If you're one of them, check if your chosen software has a mobile app or if you can access it using a mobile browser.

Lastly, consider your budget while choosing a video transcription tool. Though many free tools deliver fantastic results, upgrading to their paid versions can provide features that could arguably be useful if you are a regular live streamer. This includes faster transcription, overdubbing, and much more.

Now that you know what to consider while choosing a transcription tool for your live videos, let's walk you through our top picks:

In transcription-land, many products are boosted by exceptional AI, reshaping the scene. Lately is one of them. Its super artificial intelligence makes it a must-have tool.

While its transcription service is top-notch, the best part is that in addition to transcribing your audio and video files, it can also automatically turn your long-form videos into several clips that are great for sharing across social media. This in itself can save you a lot of time generating content for your channels.

So, if you want a tool that not only transcribes but takes away the hard work of creating clips for social media and much more, Lately, with plans starting at $9/month, worth considering.

2. Descript

If live streams are your life – whether you do a lot of Q&As, interviews, or just fun live broadcasts – Descript is the best video transcription software out there, with powerful accuracy and collaboration. Besides boasting cloud sync for instant access from wherever you are, it also ensures excellent safety and security for your data.

Using this tool, you can transcribe audio in 22 new languages and even remove filler words. It also automatically adds speaker labels, and you can even add a voiceover to videos using the text-to-speech feature.

Descript prioritizes user convenience, and the result is easy transcript export in multiple formats with timestamps. Its free plan gives you 3 hours of free transcription, and paid plans start from $12 a month.

If you need a video transcription tool with an in-browser editor, Sonix could be the best option around. With features like search, play, edit, and share your transcripts, it's a time saver for live streamers. You can even organize the transcripts with multi-folder nesting.

It can also translate into more than 35 languages and automatically labels speakers. What's more? You get timestamps, and the tool even separates speech into paragraphs.

The standard plan works on the pay-as-you-go mechanism, costing $10 an hour. However, you can get a subscription starting from $22/month and cut the hourly rate to $5 while enjoying automated timecode realignment, multitrack uploads, etc.

4. oTranscribe

It's hard to go wrong with a reliable, easy-to-use, browser-based platform, and OTranscribe is just that. This video transcription tool allows you to handle the audio/video player and text editor in the same window. To help you further skip the tab juggling, it also lets you create keyboard shortcuts that suit your transcribing style.

There's also a feature of interactive timestamps for better text navigation, and the tool saves all your progress automatically to your browser's storage.

If you are looking for a free, open-source transcription tool that offers hassle-free handling, this one is a great choice.

Sure, Otter may be the talk of the town, but we'd say it's worth the hype. With features like real-time automated notes, customized vocabulary, and summary keywords, it's an all-rounder.

It lets live streamers collaborate better with their teams by highlighting and inserting comments. There's also speaker identification, keyword search, adjustable playback speeds, and more. The tool is available to use in a web browser or through an iOS or Android app.

Otter's free plan gives 600 free minutes of monthly transcription, and paid plans start from $8.33/month, offering 6,000 minutes of monthly transcription, automatic sync of audio/video files from Dropbox, advanced search, etc.

6. Fireflies

Fireflies is an excellent video transcription tool that can help you record, transcribe, and search through your video content. Like most of its rivals, this one also offers the option to add comments or mark specific sections of your video to collaborate with your team.

If you fancy a Chrome extension for easy transcribing, you can even get that in addition to options like uploading your video files or using the native integrations.

The free plan gives 800 mins/storage seat, and paid plans start from $10/month.

7. SpeedScriber

If you are looking for a macOS-only transcription software, SpeedScriber is your best bet. It supports multiple accents and speakers, and you can even assign a name and color to each speaker for easy accessibility.

Moreover, the software adds timestamps automatically. Besides, you can upload your video files from Finder or clips from Apple Final Cut Pro X.

With multiple export options and transcription charged hourly from $0.37 to $0.50 per minute, it's perfect for users who need quick transcription without spending too much on the solution.

What if you get a video transcription tool that can add captions and voiceovers too? Well, Maestra does it all – at the click of a button.

It supports over 50 languages, and you can edit your automatically generated transcripts with absolute ease. Starting from   $29/month for 5 hours per month, this tool lets you generate 150+ unique voices, create teams and channels, and do a lot more.

Thanks to its proprietary algorithm, Temi remains a popular choice for video transcription software. Temi's claim to fame is up to 95% accuracy for good quality audio, and we couldn't agree more. With minimal background noise, clear speaker(s), and minimal accents, you can achieve terrific results using this speech recognition software.

There's also a transcription editor, which lets you add timestamps and clean up the transcript. You can even synchronize transcripts with slides.

While the free trial is available for one transcript of up to 45 minutes, pricing starts at $0.25 per minute.

10. Go Transcribe

Heads up to live streamers who often find it difficult to streamline their workflow: Go Transcribe can be your favorite cloud-based transcription platform. Featuring a unique online editor to search audio and make changes in your transcription, this one also lets you download the transcripts into multiple formats.

Much like its competitors, Go Transcribe also lets you highlight and comment on different sections of the transcripts. But what sets it apart from most of its contenders is the enterprise-grade security it offers.

With its pay-as-you-go plan starting at $12/hour, it's a great choice for those who need fast turnarounds only for their transcripts.

An aesthetically pleasing and pretty powerful tool, Rev is designed to ease transcribing audio or video for multitaskers. It offers many benefits, including its searchable, 90%+-accurate automated transcription. The best thing about Rev is that its speech engine has been trained on 50,000+ hours of human-transcribed content. This content covers a range of topics, industries, and accents.

If speed and accuracy are what you seek, you'd love the results Rev produces through its transcribed files, available in minutes. You can experience its awesomeness for $0.25 per minute. And you can also get human transcription services and enjoy 99% accuracy for $1.50 per minute.

Did You Find The Right Video Transcription Tool?

Ready to automate your video transcription needs? We hope the list above helps you find the right tool to create transcripts. To learn more about creating a video transcript from a live stream, check this guide.

Start creating with StreamYard today

Speech to Text, Live Captions & Translations

Enhance any meeting, speech or event, in-person or online, with automatic live captioning & translations..

* Alpha (α) release

About Speechlogger Live Captions

Speechlogger started in 2015 as a pioneer in live captioning and instant translations. The traditional version of Speechlogger is still available today. Many of our users were using Speechlogger in order to broadcast their captioned speech via screen share. In addition, many requested us for live captions (and translations) for phone calls, meetings and events - whether in-person, live or online. That's where Speechlogger Live Captions comes in. Speechlogger Live, transcribes and translates in real time, just as the traditional Speechlogger, but in addition it enables broadcasting live captions to other participants and attendees, as well as having multiple speakers sharing a live-captions room.

This opens the use of Speechlogger Live for many use cases - such as:

• Meeting protocols - generate meeting notes of online or phone-based meetings with a single click
• Live, hybrid and online conferences & webinars - broadcast speakers' captioned speech as well as live translations
• Accessibility for the hard-of-hearing - use in live events, speeches, online and regular phone calls, webinars, etc.
• Accessibility for different language speakers - use in live events, speeches, online and regular phone calls, webinars, etc.

Currently in alpha version - go ahead - give it a try - and please let us know if you have any feedback for us. Thank you!

Limited time for testing this alpha release - this service is 100% free!

Main Features

Automatic transcriptions (Speech to Text)

Share, broadcast live captions, real time translations, read out loud translated captions, multilingual, speaker tags and font color, download / print transcript, dark mode, settable font size and more, works in parallel to any other online meeting app, attendees can join in from any platform, including their personal phones.

• Just for this alpha release
• For limited time
• All features are free!
• Please - one request - try it and send us feedback.

Additional text-speech services and products by us

Files Transcriptions

Automatically transcribes your audio or video recordings. Fast - results within minutes. Affordable - a tenth of the cost of a human transcriptionist. Private - no human involved, no logs kept other than in your account.

Speechnotes Dictation Notepad

Probably the most loved, reliable and battle tested online voice enabled notepad. Lightweight, simple to use and robust. Loved by millions worldwide.

TTSReader - Text to Speech

I NSTANTLY READS OUT LOUD TEXT, PDFS & EBOOKS WITH NATURAL SOUNDING VOICES ONLINE - WORKS OUT OF THE BOX. DROP THE TEXT AND CLICK PLAY.

Voice Typing for Chrome

Voice-type anywhere, on any website with this Chrome extension. In addition, add emojis with a single click.

Live Captions

Broadcast live captions and instant translations

Legacy Speechlogger

The good old first edition of Speechlogger.

BSR CITY TOWERS, I-120 Petah Tikva, Israel

Feedback & Support Form

[email protected]

Getting started

An introduction to getting transcription data from live streaming audio in real time using Deepgram's SDKs.

In this guide, you'll learn how to automatically transcribe live streaming audio in real time using Deepgram's SDKs , which are supported for use with the Deepgram API .

📘 Before you run the code, you'll need to follow the steps in this guide to create a Deepgram account, get a Deepgram API key, configure your environment, and install the SDK of your choice.

Transcribe Audio

Follow the steps to transcribe audio from a remote audio stream. If you would like to learn how to stream audio from a microphone, check out our Live Audio Starter Apps or specific examples in the readme of each of the Deepgram SDKs .

🌈 For those who prefer to work from a Jupyter notebook, check out our Python Starter Notebooks .

Install the SDK

Open your terminal, navigate to the location on your drive where you want to create your project, and install the Deepgram SDK:

Add Dependencies

Add necessary external dependencies to your project.

Write the Code

In your terminal, create a new file in your project's location, and populate it with code.

ℹ️ The above example includes the parameter model=nova-2 , which tells the API to use Deepgram's most powerful and affordable model. Removing this parameter will result in the API using the default model, which is currently model=base . It also includes Deepgram's Smart Formatting feature, smart_format=true . This will format currency amounts, phone numbers, email addresses, and more for enhanced transcript readability.

Start the Application

Run the application from the terminal.

See Results

Your transcripts will appear in your browser's developer console. Keep in mind that Deepgram does not store transcriptions. Make sure to save the output or return transcriptions to a callback URL for custom processing .

By default, Deepgram live streaming looks for any deviation in the natural flow of speech and returns a finalized response at these places. To learn more about this feature, see Endpointing .

Deepgram live streaming can also return a series of interim transcripts followed by a final transcript. To learn more, see Interim Results .

ℹ️ Endpointing can be used with Deepgram's Interim Results feature. To compare and contrast these features, and to explore best practices for using them together, see Using Endpointing and Interim Results with Live Streaming Audio .

If your scenario requires you to keep the connection alive even while data is not being sent to Deepgram, you can send periodic KeepAlive messages to essentially "pause" the connection without closing it. To learn more, see KeepAlive .

What's Next?

Now that you've gotten transcripts for streaming audio, enhance your knowledge by exploring the following areas. You can also check out our Live Streaming API Reference for a list of all possible parameters.

Try the Starter Apps

Clone and run one of our Live Audio Starter App repositories to see a full application with a frontend UI and a backend server streaming audio to Deepgram.

Read the Feature Guides

Deepgram's features help you to customize your transcripts. Do you want to transcribe audio in other languages? Check out the Language feature guide. Do you want to remove profanity from the transcript or redact personal information such as credit card numbers? Check out Profanity Filtering or Redaction .

Take a glance at our Feature Overview for streaming speech-to-text to see the list of all the features available. Then read more about each feature in its individual guide.

Add Your Audio

Ready to connect Deepgram to your own audio source? Start by reviewing how to determine your audio format and format your API request accordingly.

Then, you'll want to check out our Live Streaming Starter Kit . It's the perfect "102" introduction to integrating your own audio.

Explore Use Cases

Learn about the different ways you can use Deepgram products to help you meet your business objectives. Explore Deepgram's use cases .

Transcribe Pre-recorded Audio

Now that you know how to transcribe streaming audio, check out how you can use Deepgram to transcribe pre-recorded audio. To learn more, see Getting Started with Pre-recorded Audio .

Updated 3 months ago

• Feature Overview

Speech to Text Converter

Descript instantly turns speech into text in real time. Just start recording and watch our AI speech recognition transcribe your voice—with 95% accuracy—into text that’s ready to edit or export.

How to automatically convert speech to text with Descript

Create a project in Descript, select record, and choose your microphone input to start a recording session. Or upload a voice file to convert the audio to text.

As you speak into your mic, Descript’s speech-to-text software turns what you say into text in real time. Don’t worry about filler words or mistakes; Descript makes it easy to find and remove those from both the generated text and recorded audio.

Enter Correct mode (press the C key) to edit, apply formatting, highlight sections, and leave comments on your speech-to-text transcript. Filler words will be highlighted, which you can remove by right clicking to remove some or all instances. When ready, export your text as HTML, Markdown, Plain text, Word file, or Rich Text format.

Download the app for free

More articles and resources.

New: Free Overdub on all Descript accounts, with easier voice cloning

What is a video crossfade effect?

New one-click integrations with Riverside, SquadCast, Restream, Captivate

Other tools from descript, voice cloning, video collage maker, advertising video maker, facebook video maker, youtube video summarizer, rotate video, marketing video maker.

Speech to Text

• 3 Create a new project Drag your file into the box above, or click Select file and import it from your computer or wherever it lives.

Expand Descript’s online voice recognition powers with an expandable transcription glossary to recognize hard-to-translate words like names and jargon.

Record yourself talking and turn it into text, audio, and video that’s ready to edit in Descript’s timeline. You can format, search, highlight, and other actions you’d perform in a Google Doc, while taking advantage of features like  text-to-speec h, captions, and more.

Go from speech to text in over 22 different languages, plus English. Transcribe audio in  French ,  Spanish , Italian, German and other languages from around the world. Finnish? Oh we’re just getting started.

Yes, basic real-time speech to text conversion is included for free with most modern devices (Android, Mac, etc.) Descript also offers a 95% accurate text-to-speech converter for up to 1 hour per month for free.

Speech-to-text conversion works by using AI and large quantities of diverse training data to recognize the acoustic qualities of specific words, despite the different speech patterns and accents people have, to generate it as text.

Yes! Descript‘s AI-powered Overdub feature lets you not only turn speech to text but also generate human-sounding speech from a script in your choice of AI stock voices.

Descript supports speech-to-text conversion in Catalan, Finnish, Lithuanian, Slovak, Croatian, French (FR), Malay, Slovenian, Czech, German, Norwegian, Spanish (US), Danish, Hungarian, Polish, Swedish, Dutch, Italian, Portuguese (BR), Turkish.

Descript’s included AI transcription offers up to 95% accurate speech to text generation. We also offer a white glove pay-per-word transcription service and 99% accuracy. Expanding your transcription glossary makes the automatic transcription more accurate over time.

Navigation Menu

Search code, repositories, users, issues, pull requests..., provide feedback.

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly.

To see all available qualifiers, see our documentation .

• Notifications You must be signed in to change notification settings

A nearly-live implementation of OpenAI's Whisper.

collabora/WhisperLive

Folders and files.

Repository files navigation

Whisperlive.

This project is a real-time transcription application that uses the OpenAI Whisper model to convert speech input into text output. It can be used to transcribe both live audio input from microphone and pre-recorded audio files.

Installation

• Install PyAudio and ffmpeg
• Install whisper-live from pip

Setting up NVIDIA/TensorRT-LLM for TensorRT backend

• Please follow TensorRT_whisper readme for setup of NVIDIA/TensorRT-LLM and for building Whisper-TensorRT engine.

Getting Started

The server supports two backends faster_whisper and tensorrt . If running tensorrt backend follow TensorRT_whisper readme

Running the Server

• Faster Whisper backend
• TensorRT backend. Currently, we recommend to only use the docker setup for TensorRT. Follow TensorRT_whisper readme which works as expected. Make sure to build your TensorRT Engines before running the server with TensorRT backend.

Controlling OpenMP Threads

To control the number of threads used by OpenMP, you can set the OMP_NUM_THREADS environment variable. This is useful for managing CPU resources and ensuring consistent performance. If not specified, OMP_NUM_THREADS is set to 1 by default. You can change this by using the --omp_num_threads argument:

Single model mode

By default, when running the server without specifying a model, the server will instantiate a new whisper model for every client connection. This has the advantage, that the server can use different model sizes, based on the client's requested model size. On the other hand, it also means you have to wait for the model to be loaded upon client connection and you will have increased (V)RAM usage.

When serving a custom TensorRT model using the -trt or a custom faster_whisper model using the -fw option, the server will instead only instantiate the custom model once and then reuse it for all client connections.

If you don't want this, set --no_single_model .

Running the Client

• lang : Language of the input audio, applicable only if using a multilingual model.
• translate : If set to True then translate from any language to en .
• model : Whisper model size.
• use_vad : Whether to use Voice Activity Detection on the server.
• save_output_recording : Set to True to save the microphone input as a .wav file during live transcription. This option is helpful for recording sessions for later playback or analysis. Defaults to False .
• output_recording_filename : Specifies the .wav file path where the microphone input will be saved if save_output_recording is set to True .

It connects to the server running on localhost at port 9090. Using a multilingual model, language for the transcription will be automatically detected. You can also use the language option to specify the target language for the transcription, in this case, English ("en"). The translate option should be set to True if we want to translate from the source language to English and False if we want to transcribe in the source language.

• Transcribe an audio file:
• To transcribe from microphone:
• To transcribe from a RTSP stream:
• To transcribe from a HLS stream:

Browser Extensions

• Run the server with your desired backend as shown here .
• Transcribe audio directly from your browser using our Chrome or Firefox extensions. Refer to Audio-Transcription-Chrome and Audio-Transcription-Firefox for setup instructions.

Whisper Live Server in Docker

• Faster-Whisper

Note : By default we use "small" model size. To build docker image for a different model size, change the size in server.py and then build the docker image.

Future Work

• Add translation to other languages on top of transcription.
• TensorRT backend for Whisper.

We are available to help you with both Open Source and proprietary AI projects. You can reach us via the Collabora website or [email protected] and [email protected] .

Releases 12

Contributors 22.

• Python 72.2%
• JavaScript 19.7%

Colleen Long, Associated Press Colleen Long, Associated Press

Will Weissert, Associated Press Will Weissert, Associated Press

Leave your feedback

• Copy URL https://www.pbs.org/newshour/politics/watch-live-biden-addresses-supreme-court-ruling-on-presidential-immunity-and-trump

WATCH: ‘No one is above the law,’ Biden says after Supreme Court ruling on presidential immunity and Trump

WASHINGTON (AP) — President Joe Biden is seeking to put the focus squarely onto Donald Trump following his uneven debate performance last week.

Watch Biden’s remarks in the player above.

Speaking Monday after the U.S. Supreme Court ruling granting broad immunity from prosecution to Trump and other presidents, Biden said the high court’s ruling had undermined the rule of law. The court’s conservative majority ruling makes it all but certain that the Republican will not face trial in Washington ahead of the November election over his actions during the violent riot on Jan. 6, 2021.

READ MORE: What does the Supreme Court immunity ruling mean for Trump? 6 questions answered

“No one is above the law, not even the president of the United States,” Biden said from the White House.

During his brief remarks he made no mention of last week’s debate or his performance, and did not take questions.

Educate your inbox

Subscribe to Here’s the Deal, our politics newsletter for analysis you won’t find anywhere else.

Thank you. Please check your inbox to confirm.

Biden seemed relaxed and confident, striking a clear and crisp tone and looking tanned and rested — all of which was in stark contrast to his often halting performance during last week’s debate, when his face was notably pale. The president also had the benefit of a teleprompter for his remarks about the court, something he didn’t have while facing off with Trump.

“I know I will respect the limits of presidential power as I have for the three-and-a-half years, but any president, including Donald Trump, will now be free to ignore the law,” Biden said.

For all the public efforts to shift the focus away from his uneven performance that spooked donors and prompted Democratic anxiety, there have been private discussions on what more Biden could do to counteract what Americans saw during the debate, when he gave convoluted answers, trailed off at times, occasionally stared blankly and sounded raspy-voiced.

There has been talk about whether Biden should be seen more in public through town-hall-style events or interviews and press conferences, which he has generally avoided during his time in office.

But most in his orbit are waiting on more substantial polling to come back in order to assess how bad the damage was before altering course in any substantial way. That’s according to four Biden advisers who were not authorized to speak publicly about internal discussions and spoke to The Associated Press on condition of anonymity.

Biden’s team may not alter anything at all. Many think — or hope — the fraught moment will pass, particularly after Biden’s family encouraged him to stay in the race and keep fighting during a huddle at Camp David on Sunday.

Campaign officials said Monday they had nothing to announce on new events. They said Biden would be campaigning as he has been, hitting battleground states as he has already been doing for months.

An ad released Monday was called “I Know” using clips from Biden’s post-debate North Carolina rally, where he said, “When you get knocked down, you get back up.”

Quentin Fulks, Biden’s principal deputy campaign manager, put the focus on Trump in a call with reporters, saying, “When you do see President Biden out on the trail, he will be talking about the reasons why Americans should be scared of Donald Trump, as he has been for months.”

Even before the debate, the age of the 81-year-old Democratic president had been a liability with voters, and the prime-time faceoff put the issue front-and-center before perhaps the largest audience he will have in the four months until Election Day. CNN, which held the debate, said more than 51 million people watched.

“I think his age was baked in, to a large degree, and I know he can do better than he did on Thursday night. I expected to see better. I’m not sure other voters did,” said Jennifer Palmieri, a White House communications director during the Obama administration and a spokesperson for Hillary Clinton’s 2016 campaign.

She added that, tactically, the campaign has responded by promoting Biden’s strong speech in North Carolina on Friday and by continuing to post strong fundraising numbers. Palmieri also said Biden might also want to sit for more interviews to continue to show that the debate was an anomaly.

“Their focus needs to be on getting him in front of voters that matter the most, and more interviews should be part of that. Don’t be like Trump in your own little universe,” she said. “For now, we’re early, but what they’re doing is working.”

There’s a sense that voters may now be watching Biden more closely for signs that show one way or another whether his debate debacle was a blip — whether he is, as he says, capable of doing the job.

Alan Kessler, a lawyer and member of the Biden campaign’s national finance team, has spent days calming jittery donors, telling them what he says he has personally witnessed when he’s seen the president — that he’s “lucid, strong as he’s always been.”

“To the extent it’s necessary, I’m reassuring people,” Kessler said.

Rebecca Katz, a strategist who worked with Democratic Pennsylvania Sen. John Fetterman’s winning campaign in 2022, saw potential parallels in Fetterman’s comeback from a shaky debate performance after he had a stroke.

Fetterman’s team highlighted especially bombastic comments his opponent made about abortion during that debate, and also had the candidate travel extensively afterward. He did lots of local television interviews to ensure voters in key markets saw him outside of clips from the debate.

“It’s not a perfect comparison but there is a blueprint for the Biden campaign,” Katz said. “You can have a rough debate night and still win.”

Biden expressed interest in doing at least one interview. At a Saturday fundraiser in East Hampton, New York, Biden said he had spoken with the broadcaster Howard Stern, who had interviewed him in April, where he answered open-ended questions mostly about his early years.

The president told the crowd he was ready for another sit-down with Stern, saying: “I had a great time on his show. And I’m actually going to take a chance in going back.”

The Democratic National Committee and Biden’s campaign, meanwhile, kept up damage control, holding an evening finance call. Over the weekend, they held calls with donors and one with dozens of committee members across the country — some of the most influential members of the party. They offered a rosy assessment of the path forward and gave no opportunity for others on the call to ask questions.

Multiple committee members on the weekend call, most granted anonymity to talk about the private discussion, described feeling like they were being asked to ignore a serious predicament.

Campaign officials have said there was no discussion “whatsoever” of Biden exiting the race nor of any staff shakeups following the debate.

Democratic Sen. Bob Casey of Pennsylvania said he thought voters were more concerned with the issues at stake, anyway. “I’ve been at this a while, and I know his work,” Casey said.

The window of opportunity for that is shrinking anyway. The Democratic National Committee has announced that it will use a virtual roll call to formally make him the nominee before the convention begins in Chicago on Aug. 19. But when that will happen and what it will look like is still unclear.

Associated Press Writers Josh Boak, Michael Rubinkam in Scranton, Pa., and Thomas Beaumont in Des Moinse, Iowa contributed to this report.

Support Provided By: Learn more

Breaking down Supreme Court decisions on Jan. 6 cases, homeless camps and agency power

Politics Jun 28

National Politics | Watch Donald Trump’s speech at his Chesapeake…

Share this:.

• Click to share on Facebook (Opens in new window)
• Click to share on X (Opens in new window)

e-Pilot Evening Edition

• Latest Headlines
• Environment

National Politics

National politics | watch donald trump’s speech at his chesapeake rally.

Former President Donald Trump held a campaign rally at the Historic Greenbrier Farms, just off the Chesapeake Expressway. This stream has ended. To read more about Trump’s Chesapeake visit, read our report .

More in National Politics

National Politics | Biden heads into a make-or-break stretch for his imperiled presidential campaign

SUBSCRIBER ONLY

National politics | zelenskyy challenges trump to reveal plans for quick end to war.

National Politics | In blockbuster term, Supreme Court boosts its own sway

National Politics | Analysis: Republicans are downplaying abortion, but it keeps coming up

Trending nationally.

• Hot topic: Florida barred heat protection for workers, now Feds are stepping in
• Rudy Giuliani disbarred, loses New York law license
• US Supreme Court passes on preliminary Illinois gun ban case but Justice Clarence Thomas calls the law ‘highly suspect’
• Ivanka Trump breaks silence on dad’s conviction in hush money case
• Manatee spotted in Virginia Beach’s Rudee Inlet

• Español – América Latina
• Português – Brasil
• Cloud Speech-to-Text
• Documentation

Transcribe streaming audio from a microphone

Transcribe streaming audio from a microphone.

Explore further

For detailed documentation that includes this code sample, see the following:

• Transcribe audio from streaming input

Code sample

To learn how to install and use the client library for Speech-to-Text, see Speech-to-Text client libraries . For more information, see the Speech-to-Text Go API reference documentation .

To authenticate to Speech-to-Text, set up Application Default Credentials. For more information, see Set up authentication for a local development environment .

To learn how to install and use the client library for Speech-to-Text, see Speech-to-Text client libraries . For more information, see the Speech-to-Text Java API reference documentation .

To learn how to install and use the client library for Speech-to-Text, see Speech-to-Text client libraries . For more information, see the Speech-to-Text Node.js API reference documentation .

To learn how to install and use the client library for Speech-to-Text, see Speech-to-Text client libraries . For more information, see the Speech-to-Text Python API reference documentation .

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser .

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License , and code samples are licensed under the Apache 2.0 License . For details, see the Google Developers Site Policies . Java is a registered trademark of Oracle and/or its affiliates.

• New Hampshire
• North Carolina
• Pennsylvania
• West Virginia
• Online hoaxes
• Coronavirus
• Health Care
• Immigration
• Environment
• Foreign Policy
• Kamala Harris
• Donald Trump
• Mitch McConnell
• Hakeem Jeffries
• Ron DeSantis
• Tucker Carlson
• Sean Hannity
• Rachel Maddow
• PolitiFact Videos
• 2024 Elections
• Mostly True
• Mostly False
• Pants on Fire
• Biden Promise Tracker
• Trump-O-Meter
• Latest Promises
• Our Process
• Who pays for PolitiFact?
• Advertise with Us
• Suggest a Fact-check
• Corrections and Updates
• Newsletters

Stand up for the facts!

Our only agenda is to publish the truth so you can be an informed participant in democracy. We need your help.

I would like to contribute

2024 presidential debate fact-check: how accurate were joe biden, donald trump.

From left, former President Donald Trump and President Joe Biden debate June 27, 2024, in Atlanta. (AP)

President Joe Biden and former President Donald Trump, the presumptive Democratic and Republican presidential nominees, shared a debate stage June 27 for the first time since 2020, in a feisty confrontation that — thanks to debate rules — managed to avoid the near-constant interruptions that marred their previous meetings.

Biden, who spoke in a raspy voice at the debate’s start, struggled at times, at one point saying that his administration "finally beat Medicare." After the debate, during a stop at a Waffle House, Biden told reporters he had a sore throat, according to the pool report.

Trump, meanwhile, repeated numerous falsehoods, including that Democrats want doctors to be able to abort babies after birth.

Trump attacked Biden’s record, blaming inflation and other issues on Biden’s "insane and stupid policies." Biden questioned Trump’s conduct, noting that Trump is a convicted felon and saying he has the "morals of an alley cat."

CNN hosted the debate, which had no audience, at its Atlanta studio. CNN anchors Jake Tapper and Dana Bash moderated. The debate format allowed CNN to mute candidates’ microphones when it wasn’t their turn to speak.

Biden and Trump clashed on the economy, immigration and abortion, and revisited discussion of their ages. Biden is 81; Trump is 78.

Read by topic: 

Immigration Abortion Inflation and economy Jobs Trump legal cases Social Security, Medicare and taxes Checking the record on Hitler comment and Charlottesville Crime Health care Foreign policy and terrorism Election denial and Jan. 6, 2021, attack on the U.S. Capitol Worst president rankings The golf moment

Trump: Biden "allowed millions of people to come in here from prisons, jails and mental institutions."

Pants on Fire! Immigration officials arrested about 103,700 noncitizens with criminal convictions (whether in the U.S. or abroad) from fiscal years 2021 to 2024, federal data shows. That accounts for people stopped at and between ports of entry.

Not everyone was let in. The term "noncitizens" includes people who may have had legal immigration status in the U.S. but were not U.S. citizens.

The data reflects the people that the federal government knows about, but it’s inexhaustive. However, immigration experts said despite the data’s limitations, there is no evidence to support Trump’s statement.

Biden: "I've changed (the law) in the way that now you're in a situation where there are 40% fewer people coming across the border illegally."

Mostly True . The Department of Homeland Security announced that illegal immigration encounters dropped by 40%, to fewer than 2,400 each day , in the weeks after Biden announced a policy largely barring asylum access for people entering the U.S. at the southern border. The policy was announced June 4.

But immigration experts caution that it’s difficult to pinpoint a single reason for any change in border crossings. For example, other factors, such as hot weather , can affect migration patterns.

Since the policy was announced only a few weeks ago, it’s unclear whether the drop in illegal immigration will continue . 

Colleen Putzel-Kavanaugh, associate policy analyst at the Migration Policy Institute, told PolitiFact the policy could have a short-term deterrent effect. But Adam Isacson, defense oversight director at the Washington Office on Latin America, a research group, told PolitiFact, that no crackdown in the past decade has had a lasting impact.  

Trump: "We had the safest border in the history of our country."

Mostly False . Illegal immigration between ports of entry at the U.S. southern border dropped in 2017,  Trump’s first year in office, compared with previous years. Apprehensions then rose, and dropped again in 2020. When the COVID-19 pandemic started, immigration dropped drastically worldwide as governments enacted policies limiting people’s movement.

In the months before Trump left office, illegal immigration was rising again. A spike in migrants , especially unaccompanied minors , started in the spring 2020 during the Trump administration and generally continued to climb each month.

Illegal immigration during Trump’s administration was higher than under both of former President Barack Obama’s terms. 

Biden: While talking about a bipartisan border bill, "by the way, the Border Patrol endorsed me, endorsed my position."

Half True . The National Border Patrol Council — the U.S. Border Patrol’s union endorsed a bipartisan border security bill in February. But it didn’t endorse Biden.

Here's what Brandon Judd, the union’s president, said about the bill in February:

"While not perfect, the Border Act of 2024 is a step in the right direction and is far better than the current status quo. This is why the National Border Patrol Council endorses this bill and hopes for its quick passage."

Biden also supported the bill and said he would sign it into law if it passed. The bill failed in the Senate on a 49-50 vote .

However, Judd and the Border Patrol union have been critical of Biden and his immigration policies and endorsed Trump in the 2020 election.

"To be clear, we never have and never will endorse Biden," the National Border Patrol Council said in an X post during the debate.

Trump: Biden allowed in "18 million people."

False . Immigration officials have encountered immigrants illegally crossing the border 9.7 million times under Biden’s presidency. When accounting for "got aways" — people who aren’t stopped by border officials — the number rises to about 11.4 million. 

But encounters don’t mean admissions . Encounters represent events, so one person who tried to cross the border twice counts for two encounters. Also, not everyone encountered is let in. Many encounters result in deportations. The Department of Homeland Security estimates about 4 million encounters have led to expulsions or removals.

Trump: "The problem (Democrats) have is they're radical, because they will take the life of a child in the eighth month, the ninth month, and even after birth." False. Willfully terminating a newborn’s life is infanticide and is illegal in every U.S. state. 

Most elected Democrats who have spoken publicly about this have said they support abortion under Roe v. Wade’s standard, which provided abortion access up to fetal viability. This is typically around 24 weeks of pregnancy, when the fetus can survive outside of the womb. Many of these Democrats have also said they support abortions past this point if the treating physician deems it necessary. Medical experts say situations resulting in fetal death in the third trimester are rare — less than 1% of abortions in the U.S. occur after 21 weeks — and typically involve fatal fetal anomalies or life-threatening emergencies affecting the pregnant woman. For fetuses with very short life expectancies, doctors may induce labor and offer palliative care. Some families choose this option when facing diagnoses that limit their babies’ survival to minutes or days after delivery. Some Republicans who have made claims similar to Trump’s point to Democratic support of the Women’s Health Protection Act of 2022 , citing the bill’s provisions that say providers and patients have the right to perform and receive abortion services without certain limitations or requirements that would impede access. Anti-abortion advocates say the provisions in the bill, which failed to advance 49-51, would have created a loophole that eliminated any limits to abortions later in pregnancy. Alina Salganicoff, director of KFF’s Women’s Health Policy program, said the legislation would have allowed health providers to perform abortions without obstacles such as waiting periods, medically unnecessary tests and in-person visits, or other restrictions. The bill would have allowed an abortion after viability when, "in the good-faith medical judgment of the treating health care provider, continuation of the pregnancy would pose a risk to the pregnant patient’s life or health."

Trump: "He caused this inflation. I gave him a country with … essentially no inflation. It was perfect."

Mostly False . When Biden was inaugurated, year-over-year inflation was about 1.4%. However, that was shaped by the still-weak economy during the coronavirus pandemic, which was still a serious threat when Biden was inaugurated.

As the pandemic conditions improved, the economy accelerated. Consumers were ready to buy products, but the pandemic had prompted supply chain shortages. This, combined with Russia’s invasion of Ukraine which raised gasoline prices, led to inflation, peaking at 9% about a year and a half into Biden’s presidency. That was the highest in about four decades. 

Economists generally say Biden’s coronavirus relief plan, the American Rescue Plan, did exacerbate inflation by putting more money into consumers’ hands at a time when supplies were running short. But they do not believe that Biden caused high inflation single-handedly.

Trump: "You look at the cost of food, where it's double, triple and quadruple."

False.  Food costs have risen faster under President Joe Biden than under any of his five most recent predecessors. However, the 21% increase in food prices on Biden’s watch is well below what Trump claimed. Quadrupling food costs would be an increase of 300%, or more than 10 times larger than what Trump said.

Specific categories of food have spiked more than food prices overall. For instance, egg prices are 84% higher today than when Biden took office. But for every food category that has outrun overall food inflation, there’s another category that has risen more slowly than average.

Also, this increase was spread over three and a half years, making the annual increase about 6%, part of which has been offset by rising wages .

Biden: "Economists say (Trump’s proposed tariffs are) going to cost the average American $2,500 a year or more."

Mostly True. Most economists expect that Trump’s proposed 10% across-the-board tariff on foreign products will force consumers to pay more. The specific size of that hit is open to debate, though Biden offered a figure somewhat higher than current estimates.

Just days before the debate, the American Action Forum, a center-right think tank, projected additional costs per household of $1,700 to $2,350 annually.

The Peterson Institute of International Economics, another Washington, D.C.-based think tank, projected that such tariffs would cost a middle-income household about $1,700 extra each year.

Biden: Semiconductor jobs "to build these chips … pay over $100,000. You don’t need a college degree for them."

Mostly False . The average semiconductor industry salary is around $170,000, figures from Oxford Economics and Semiconductor Industry Association, a trade group, show. But this figure includes all jobs within the industry and doesn’t single out jobs requiring no college degree.

To earn a salary of $110,000 or higher, employees in the semiconductor industry need undergraduate or graduate-level degrees, the groups say.

The most a person would make without a four-year degree is about $70,000, according to a 2021 report from the Semiconductor Industry Association and Oxford Economics.

Biden: "Black unemployment is the lowest level it’s been in a long, long time."

Mostly True .  The record for low Black unemployment rate was set under Biden in April 2023, at 4.8%. It has risen modestly since then to 6.1% in May 2024, but that’s still lower than it was for much of the first two years under Trump. 

Overall, Trump had success on this statistic, too. When Biden set the record, the record he was breaking was Trump’s: 5.3% in August and September 2019.

Trump: "The only jobs (Biden) created are for illegal immigrants and bounce-back jobs, bounce-back from the COVID."

False . Since Biden took office in early 2021, the number of foreign-born Americans who are employed has risen by about 5.6 million. But over the same time period, the number of native-born Americans employed has increased by almost 7.4 million. (There are many more native-born Americans than foreign-born Americans, so on a percentage basis, the increase for foreign-born Americans is about 22%, compared with 6% for native-born Americans.)

It’s also wrong to say that all the foreign-born employment gains (much less all the employment gains) stem from migrants here illegally. The data for foreign-born Americans includes anyone born outside the U.S., including immigrants who have been in the United States legally for decades.

Employment on Biden’s watch passed its prepandemic level by June 2022, about a year and a half into his term. Since then, the U.S. economy has created an additional 6.2 million jobs.

Trump: Biden "indicted me because I was his opponent."

False . The Manhattan district attorney’s investigation into Trump’s business records began before Biden was president, but Biden was president by the time Trump was charged in 2023.

After Michael Cohen, who had been an attorney for Trump, pleaded guilty to federal charges in 2018, then-Manhattan District Attorney Cyrus Vance Jr. began investigating the payments, Politico reported . That was before Biden was president. Manhattan District Attorney Alvin Bragg hired a former Justice Department prosecutor in 2022. But experts told us that doesn’t prove Biden was involved.

Trump has also been indicted by a Fulton County, Georgia, grand jury and two federal grand juries. Biden is not responsible for state or federal prosecutors’ decisions to present cases to grand juries.

Trump: "Social Security, he's destroying it, because millions of people are pouring into our country, and they're putting them onto Social Security. They're putting them onto Medicare, Medicaid."  

False . It’s wrong to say that immigration will destroy Social Security. Social Security’s fiscal challenges stem from a shortage of workers compared with beneficiaries. 

Immigration is far from a fiscal fix-all for Social Security’s challenges. But having more immigrants in the United States would increase the worker-to-beneficiary ratio, potentially for decades, thus extending the program’s solvency, experts say.

Most immigrants in the U.S. illegally are also ineligible for Social Security. However, people who entered the U.S. illegally and were granted humanitarian parole — a temporary permission to stay in the country — for more than one year, are eligible for Social Security. 

Immigrants in the U.S. illegally also are generally ineligible to enroll in federally funded health care coverage such as Medicare and Medicaid. (Some states provide Medicaid coverage under state-funded programs regardless of immigration status. Immigrants are eligible for emergency Medicaid regardless of status.)

Biden: Trump "wants to get rid of Social Security, he thinks there's plenty to cut in Social Security."

False . Biden went further than previous attacks to say Trump would cut the program entirely. In a March CNBC interview , Trump said of entitlement programs such as Social Security, "There’s a lot you can do in terms of entitlements, in terms of cutting." 

However, Trump quickly walked that statement back. Also, his campaign website says that not "a single penny" should be cut from Social Security, and he’s repeated similar lines in campaign rallies.

Before the 2024 campaign, Trump said about a half dozen times that he’s open to major overhauls of Social Security, including cuts and privatization.

Trump: "He wants to raise your taxes by four times. He wants to raise everybody's taxes by four times."

False . Biden proposed a tax increase of about 7% over the next decade, which is far lower than the 300% increase that former President Donald Trump claimed. (Doubling would be a 100% increase and tripling would be a 200% increase.)

About 83% of the proposed Biden tax increase would be borne by the top 1% of taxpayers, a level that starts at just under $1 million a year in income. 

Taxpayers earning up to $60,400 would see their yearly taxes decline on average, and taxpayers earning $60,400 to $107,300 would see an annual increase of $20 on average.

Biden: "I said I’d never raise the tax on anybody if you're making less than $400,000. I didn’t."

Mostly True . Biden has said repeatedly that he will not raise taxes on anyone making less than $400,000, a promise he campaigned on in 2020 .

He has not raised any individual income taxes on Americans earning less than $400,000 a year. It’s always possible that individual taxpayers could see increases because of changes in their personal circumstances.

Some corporate tax increases enacted on Biden’s watch have a small projected pass-through effect on taxpayers. Economists generally allocate a portion of the tax burden from corporate taxes to shareholders and partly to consumers, who often pay higher prices as corporations factor the higher taxes into pricing of goods and services.

The White House has told PolitiFact that Biden would let the tax cuts Trump signed in 2017 expire for wealthier taxpayers, but would not let Americans making less than $400,000 see any tax increase. 

Trump: "I gave you the largest tax cut in history."

False . When it was passed in 2017, Trump’s tax cut was, in inflation-adjusted dollars, the fourth-largest since 1940. And as a percentage of gross domestic product, it ranked seventh in history, according to figures published by the Treasury Department.

Biden: Trump said, "I don't want to go in (a World War I cemetery in France), because they're a bunch of losers and suckers." 

Trump called this a "made-up quote." Both statements need context.

A September 2020 article in The Atlantic cited unnamed sources as saying that Trump called Americans who died in wars "suckers" and "losers" when he canceled a trip in 2018 to the Aisne-Marne American Cemetery near Paris. 

"Why should I go to that cemetery? It’s filled with losers," The Atlantic reported Trump said, citing multiple unnamed sources. In a separate conversation, also according to unnamed sources, he said U.S. Marines who lost their lives in World War I’s Battle of Belleau Wood were "suckers" for getting killed.

John Kelly, Trump’s former chief of staff, confirmed elements of The Atlantic’s story three years later in an October 2023 statement to CNN , including that Trump referred to military members who were killed or wounded as "suckers" and "losers."

But Trump has long denied these allegations.

Biden: "This is a guy who says Hitler's done some good things." 

This is a reference to a passage in a book by CNN anchor Jim Sciutto in which Kelly, Trump's former chief of staff, described a conversation he had with Trump.

"He said, ‘Well, but Hitler did some good things,’" Kelly said . "I said, ‘Well, what?’ And he said, ‘Well, (Adolf Hitler) rebuilt the economy.’"

According to the book, Kelly also told Sciutto that Hitler had the "loyalty" of his senior staff, unlike Trump.

There is no independent verification of this conversation. Trump campaign spokesperson Steven Cheung told CNN in March that Kelly suffered from "a severe case of Trump Derangement Syndrome," but didn’t address the specific allegations. 

Biden: Trump called Nazis protesting in the crowd in Charlottesville, Virginia, in 2017 "very fine people."

Trump vehemently denied Biden’s characterization. Here’s what happened. In comments to reporters following violent protests in Charlottesville, Virginia, over the removal of a Confederate general’s statue, Trump said of marchers who protested the removal, "You had some very bad people in that group, but you also had people that were very fine people, on both sides." 

During back-and-forth remarks with reporters, Trump separately condemned the "neo-Nazis and the white nationalists."

"But not all of those people were neo-Nazis, believe me," Trump said. "Not all of those people were white supremacists by any stretch."

Trump also said that counterprotesters had similar makeup of "good" and "bad" people — "some fine people" and also " troublemakers" and "bad people."

Trump: "What he's done to the Black population is horrible, including the fact that for 10 years, he called them super predators … in the 1990s."

False . In a 1993 Senate floor speech, Biden, then a U.S. senator from Delaware, spoke about doing something for young people who lacked supervision, structure or opportunities. He said the country needed to focus on them, because otherwise, a portion of them would "become the predators 15 years from now."

Biden did not single out any racial or ethnic group. In a 1998 speech at an attorneys general conference, Biden also used the term "predators." He didn’t say he was talking about Black youth.

Biden: "We brought down the price (of) prescription drug(s), which is a major issue for many people, to $15 for an insulin shot, as opposed to $400."

Half True . Biden touted his efforts to reduce prescription drug costs by referring to the $35 insulin price cap his administration instituted as part of the 2022 Inflation Reduction Act. But he flubbed the number during the debate, saying it was lowered to $15. In his closing statement, Biden corrected the number to $35.  

The price of insulin for Medicare enrollees starting in 2023 dropped to $35 a month, not $15. Drug pricing experts told PolitFact when we rated a similar claim that most Medicare enrollees were likely not paying a monthly average of $400 before the changes, although because costs vary depending on coverage phases and dosages, some might have paid that much in a given month.

Biden: Trump "wants to get rid of the ACA again."

Half True . In 2016, Trump campaigned on a promise to repeal and replace the Affordable Care Act, or ACA. In the White House, Trump supported a failed effort to do just that. In the years since, he has repeatedly said he would dismantle the health care law in campaign stops and social media posts throughout 2023.

In March, however, Trump walked back this stance, writing on Truth Social that he "isn’t running to terminate" the ACA but to make it "better" and "less expensive." Trump hasn’t said how he would do this.

Trump: "I'm the one that got the insulin down for the seniors."

Mostly False . When he was president, Trump instituted the Part D Senior Savings Model , a program that capped insulin costs to $35 a month for some older Americans in drug plans that chose to participate. 

But because it was voluntary, 38% of all Medicare drug plans , including Medicare Advantage plans, participated in 2022, according to KFF. Trump’s voluntary plan also covered only one form of each dosage and insulin type. 

Biden points to the Inflation Reduction Act’s mandatory $35 insulin cap as a major achievement. This cap applies to all Medicare prescription plans. It also expanded the cap to all covered insulin types and dosages. Although Trump’s model was a start, it did not have the sweeping reach that Biden’s mandatory cap achieved. 

Biden: "I’m the only president this century that doesn't have any, this decade, that doesn’t have any troops dying anywhere in the world like he did."

False . Some U.S. service members have died in combat abroad during Biden’s presidency.

In August 2021, 13 U.S. service members were killed in an attack as the U.S. withdrew from Afghanistan under Biden’s administration. No U.S. service member deaths were reported in 2022, Defense Department data shows. Full government data for U.S. active duty military deaths is not available for 2023 or 2024. This January, three U.S. soldiers were killed in a drone strike in Jordan.

During Trump’s presidency, from January 2017 to January 2020, 65 U.S. service members were killed in combat, Defense Department data shows.

Trump: "We had no terror (attacks) under my administration."

False . During Trump’s presidency, there were several major terror attacks, some linked to extreme global jihadist ideology. 

In 2017, there were two separate attacks in New York City, which Trump himself acknowledged as "terrorist attacks" during his 2018 State of the Union address.

There was also a December 2019 mass shooting by a member of Saudi Arabia’s air force who was studying at Naval Air Station Pensacola in Florida. Three U.S. service members were killed and eight were wounded by the gunman, who had expressed anti-American and anti-Israel sentiments on social media. Trump’s Attorney General William Barr described the shooting as "an act of terrorism."

Trump’s Justice Department also prosecuted several cases of domestic terrorism.

Excluding unsuccessful attacks and those for which officials doubt motive, there were 220 terror incidents in the United States of varying severity during Trump’s presidency from 2017 to 2020, according to the Global Terrorism Database at the University of Maryland, which tracks incidents of terrorism.

Trump: Regarding the 2020 election, "the fraud and everything else was ridiculous."

False . There is some fraud in every election, but it was not enough to change the outcome of the 2020 presidential election. And some fraudulently cast ballots involved defendants who were either registered Republicans or said that they supported Trump .

Federal and state officials , including Republicans in Georgia , said the 2020 election was legitimate. Trump’s own attorney general, William Barr, said that he had not seen fraud on a scale that would invalidate Joe Biden’s victory. 

As Trump faced reelection in 2020, he said Biden could win only if the election was rigged. Numerous investigations, court cases and reviews yielded no evidence of widespread rigging in the 2020 presidential election.

Elections are administered in thousands of local areas nationwide, each with safeguards, making any attempt to "rig" a national election highly improbable.

Trump: Pelosi said "I take full responsibility for Jan. 6."

False . That’s not what former House Speaker Nancy Pelosi, D-Calif., said.

In a 41-second video taken on Jan. 6, 2021, Pelosi said, "I take responsibility for not having them just prepare for more," referring to U.S. Capitol security. She did not say she took responsibility for the Jan. 6, 2021, Capitol attack.

Records show that Pelosi approved a Jan. 6, 2021, request to seek support from the National Guard and pushed to get National Guard troops to the U.S. Capitol when their deployment was delayed by hours that day.

Biden: Presidential historians "voted who was the worst president in American history. From best to worst. They said (Trump) was the worst in all of American history."

True . The 2024 Presidential Greatness Project Expert Survey, released in February, collected responses from 154 presidential historians, which included current and recent members of the American Political Science Association. The survey ranked Biden as the 14th best president in U.S. history, and put Trump last.

The historians were asked to give every president a score, from zero to 100. Abraham Lincoln topped the list with an average score of 95, while Biden scored an average of 62.66. Trump averaged just under 11 points.

Somehow the presidential debate turned into a fight over who’s the better golfer. Biden said he would have a driving competition with Trump and claimed he was a 6 handicap while serving as vice president.

Trump scoffed. "He can hit a ball 50 yards."

Joe Biden is currently listed with the United States Golf Association as holding a 6.7 handicap playing out of Fieldstone Golf Club in Delaware. Biden hasn’t logged a score in the system since 2018. Scores are typically self-reported, and a handicap comes from an average of the lowest 8 of the most recent 20 posted scores.

The lower the handicap you have, the better golfer you are. Ivanka Trump, for instance, is a 20.9 handicap and Eric Trump is listed as a 13.6 (without a round since 2015). Donald Trump is in the system as a member of the prestigious Winged Foot Golf Club in New York. He lists a handicap of 2.5 but hasn’t posted a score since 2021.

PolitiFact PolitiFact Executive Director Aaron Sharockman, Chief Correspondent Louis Jacobson, Senior Correspondent Amy Sherman, Staff Writers Grace Abels, Kwasi Gyamfi Asiedu, Maria Briceño, Jeff Cercone, Madison Czopek, Marta Campabadal Graus, Ranjan Jindal, Mia Penner, Samantha Putterman, Sara Swann, Maria Ramirez Uribe, Researcher Caryn Baird, KFF Health News Senior Correspondent Julie Appleby and KFF Health News Mountain States Editor Matt Volz​ contributed to this story. 

Our debate fact-checks rely on both new and previously reported work. We link to past work whenever possible. In some cases, a fact-check rating may be different tonight than in past versions. In those cases, either details of what the candidate said, or how the candidate said it, differed enough that we evaluated it anew. 

Our Sources

Sources linked in story. 

Browse the Truth-O-Meter

More by politifact staff.

Watch CBS News

Trump and Biden's first presidential debate of 2024, fact checked

By Arden Farhi , Hunter Woodall , Jui Sarwate , Julia Ingram , Layla Ferris , Laura Doan , James LaPorta , Daniel Klaidman , Alexander Tin , Pete Villasmil, Sierra Sanders

Updated on: June 28, 2024 / 9:46 AM EDT / CBS News

Here's the fact check of some of the statements made by President Biden and former President Donald Trump during the first 2024 presidential debate , which took place in Atlanta on Thursday, June 27. The two tangled on topics including immigration, the economy, abortion and their respective records. Mr. Biden seemed to ramble during many of his responses.

CBS News  covered the debate live as it happened . 

Trump claims "we had the greatest economy in the history of our country": False

Trump : "We had the greatest economy in the history of our country. And we have never done so well. Every- everybody was amazed by it. Other countries were copying us." 

Details : Trump's claim is false that during his presidency the U.S. had the greatest economy in the history of the country by many of the common metrics used to judge economic performance. The claim struggles when looking at GDP. If the 2020 pandemic  is excluded, growth after inflation under Trump averaged 2.49%, according to figures from the  World Bank . This is far from the GDP growth under Democratic President Bill Clinton of 3.88%, according to  World Bank data . Including the time period after COVID spread, that average drops to 1.18%. 

Trump's claim also falls short when compared to historical figures. Growth between 1962 to 1966 ranged from 4.4% to 6.6%. In 1950 and 1951, GDP ranged between 8.7% and 8%.

Under Mr. Biden, annual GDP growth is averaging 3.4%, according to the  Associated Press .

*An earlier version of this fact check misstated World Bank figures for growth after inflation under Trump at 2.65%, rather than 2.49%, and 1.45%, instead of 1.18%, and also rounded the growth number for Clinton. This has been updated.

Unemployment

Trump's claim is also false even when evaluating the unemployment rate.    In February 2020, a month before the COVID pandemic affected the economy, the unemployment rate stood at 3.5% — which was the lowest since December 1969 — but not the lowest ever. When Trump's term ended, the unemployment rate was 6.3%.

In 1953, the unemployment rate fell as low as 2.5%. Under Mr. Biden, the unemployment rate is 4%, according to the  most recent data  from May 2024. 

In January 2023 and again in April 2023, the unemployment rate was 3.4%, lower than the best month during Trump's term.

Stock market performance

On Jan. 19, 2021, the  S&P 500-stock average  closed at 67.8% above where it had been the day before Trump was inaugurated in 2017. 

According to  Investopedia ,  at the end of President Barack Obama's first term in office, the S&P closed 84.5% higher. Additionally the S&P gained 79% during President Bill Clinton's first term, and 70% during President Dwight Eisenhower's first term. So far, under President Biden, the  S&P 500 has increased almost 40% , according to calculations on June 13. 

By Laura Doan and Hunter Woodall 

Biden claims he's the only president this century that doesn't have troops dying anywhere in the world: False

Biden: "I'm the only president this century that doesn't have any — this decade — that doesn't have any troops dying anywhere in the world." 

Details : At least 16 U.S. service members have died while serving overseas during Mr. Biden's presidency. Thirteen U.S. service members  died  in an attack at the Kabul airport in Afghanistan in August 2021. Three soldiers were  killed  in an attack in Jordan in January of this year.

By Layla Ferris

Trump claims he did not refer to U.S. soldiers who were killed as "suckers and losers": False

Trump: "First of all, that was a made-up quote. 'Suckers and losers,' they made it up."

Details : Current and former U.S. military service members have detailed to CBS News multiple instances when Trump made disparaging remarks about members of the U.S. military who were captured or killed, including referring to the American war dead at the Aisle-Marne American Cemetery in France in 2018 as "losers" and "suckers."  

A senior Defense Department official and a former U.S. Marine Corps officer with direct knowledge of what was said detailed how Trump said he did not want to visit the cemetery because it was "filled with losers." These accounts were backed independently by two other officials — a former senior U.S. Army officer and a separate, former senior U.S. Marine Corps officer.   

In another conversation on the trip, Trump referred to the 1,800 Marines who died in the World War I battle of Belleau Wood as "suckers" for getting killed.  The Atlantic was first to report Trump's comments in 2020. His former chief of staff John Kelly later confirmed to CNN the essence of what Trump had said.

By James LaPorta and Sierra Sanders 

Biden claims 40% fewer people are crossing border illegally, better than when Trump was in office: Partially true         

Biden: "I've changed it in a way that now you're in a situation where there 40% fewer people coming across the border illegally; it's better than when he left office."

Details : Since Mr. Biden issued a  proclamation  banning most migrants from asylum at the U.S.-Mexico border in early June, illegal crossings there have dropped. In the past week, daily illegal border crossings have averaged roughly 2,000, according to internal Department of Homeland Security data obtained by CBS News. That's a 47% drop from the 3,800  daily average  in May.

During the height of a spike in migration faced by the Trump administration in 2019, Border Patrol recorded an average of 4,300 daily illegal crossings,  government data  show. But there were months during the  Covid-19 pandemic  when the Trump administration averaged fewer than 2,000 illegal border crossings.

By Camilo Montoya-Galvez

Trump claims migrants coming to U.S. and "killing our citizens at a level...we've never seen before": Misleading

Trump: "People are coming in and killing our citizens at a level like we've never seen before." 

Details :  Some migrants who are believed to have entered the U.S. along the southern border in recent years have been charged with murder and other heinous crimes in different parts of the country. They include the suspect in the high-profile murder of Georgia nursing student Laken Riley .

But while the data on this question is not comprehensive, available  studies  have found that migrants living in the country illegally do not commit crimes at a higher rate than native-born Americans. 

Government  statistics  also show a very small fraction of migrants processed by Border Patrol have criminal records in the U.S. or other countries that share information with American officials.

On COVID, Trump claims more people died under Biden administration than his: True, but needs context  

Trump: "Remember, more people died under his administration — even though we had largely fixed it — more people died under his administration than our administration, and we were right in the middle of it, something which a lot of people don't like to talk about. But [Biden] had far more people dying in his administration."

Details : More than 460,000 people had died from COVID-19 by the end of the week that Biden was inaugurated in 2021, while more than 725,000 have died in the three years since then, according to data from the  CDC . However, research has found that the counts of COVID-19 deaths, especially in the early days of the pandemic, were likely  undercounted .

By Julia Ingram and Jui Sarwate

In discussing abortion, Trump claims former Virginia governor, a Democrat, supported killing babies: False

Trump: "If you look at the former governor of Virginia, he was willing to do this — he said  'we'll put the baby aside and we'll determine what we'll do with the baby'.. .meaning we'll kill the baby."

Details : In a 2019 radio interview then-governor of Virginia Ralph Northam, in discussing late-term abortions,  addressed a hypothetical scenario in which a fetus was severely deformed or wasn't otherwise viable. He said, "the infant would be delivered, the infant would be kept comfortable, the infant would be resuscitated if that's what the mother and the family desired." 

Northam did not say the fetus should be killed. Killing a newborn baby — or infanticide — is illegal in every state, and not a single state is trying to change that. 

By Laura Doan and Daniel Klaidman

Trump claims Biden "went after" his political opponent in New York "hush money" case to damage him: False        

Trump: "[Biden] basically went after his political opponent (Trump) because he thought it was going to damage me, but when the public found out about these cases, 'cause they understand it better than he does, he has no idea what these cases are, but when they found out about these cases, you know what they did? My poll numbers went up, way up."

Details : There is no federal jurisdiction over a state case. The Manhattan district attorney's office is a  separate entity  from the U.S. Department of Justice. The department does not supervise the work of the Manhattan D.A.'s office, does not approve its charging decisions, and it does not try the D.A.'s cases.

By Pete Villasmil

Trump claims he brought insulin prices down for seniors: Misleading

Trump: "I'm the one that got the insulin down for the seniors. I took care of the seniors."

Details :  During Trump's time as president, Medicare created a voluntary program  in 2020  between some plans and insulin manufacturers that agreed to cap out-of-pocket costs for insulin at $35 per month. Around  half of  Medicare Advantage or stand-alone prescription drug plans ended up participating by 2021. 

David Ricks, CEO of insulin drugmaker Eli Lilly, has taken credit for pioneering the idea with Trump administration officials at a congressional  hearing  and in an  interview . In the same interview with STAT, Seema Verma, former Medicare agency chief in the Trump administration, gave Ricks the credit for the cap: "He is an unsung hero. He was actually the mastermind of all of this." 

Medicare  ended  the policy in 2023, after Mr. Biden signed into law the  Inflation Reduction Act , which capped insulin costs for Medicare beneficiaries — not just for the portion of plans participating in the program. The law capped insulin costs at the same amount of $35 per month.

By Alexander Tin and Hunter Woodall 

Trump claims Biden wants open borders: False

Trump: "He wants open borders. He wants our country to either be destroyed or he wants to pick up those people as voters." 

Details : When he took office, Mr. Biden reversed numerous Trump-era immigration policies, including a program that required migrants to await their asylum hearings in Mexico. U.S. Border Patrol has also reported record numbers of migrant apprehensions along the southern border during Mr. Biden's presidency. But Mr. Biden has never endorsed or implemented an "open borders" policy.

In fact, Mr. Biden has embraced some restrictive border policies that mirror rules enacted by his predecessor. In 2023, his administration published a regulation that disqualified migrants from asylum if they crossed into the country illegally after not seeking protection in a third country. 

Earlier this month, Mr. Biden enacted an even stricter policy: a proclamation that has partially shut down asylum processing along the border. His administration has also carried out over 4 million deportations, expulsions and returns of migrants since 2021, according to  government data .

Only U.S. citizens can vote in federal elections. Most who cross into the U.S. illegally are not on a path to permanent legal status, let alone citizenship. Even those who apply and win asylum — a process that typically takes years to complete — have to wait five years as permanent U.S. residents before applying for American citizenship. There's no evidence to suggest that the Biden administration's border policy is based on a desire to convert migrants into voters.

Biden claims Trump wants to get rid of Social Security: False        

Biden "[Trump] wants to get rid of Social Security. He thinks there's plenty to cut in social security. He's wanted to cut Social Security and Medicare, both times."

Details : Trump has repeatedly  said  he will try to protect Medicare and Social Security. Trump said in a March 21 Truth Social  post  that he would not "under any circumstance" allow Social Security to "be even touched" if he were president. Trump had said in a CNBC  interview  on March 11 that "there is a lot you can do" in terms of "cutting" spending under Social Security. Mr. Biden  said  the comments were proof Trump aimed to make cuts in the programs, but a Trump campaign spokesman  said  Trump was referring to "cutting waste and fraud," not Social Security entitlements.

Trump claims Biden has the "largest deficit" in history of U.S.: False

Trump: "But he's (Biden) got the largest deficit in the history of our country."

Details : The national deficit was the largest it had been in over two decades under Trump's administration, not Mr. Biden's, according to  data from the U.S. Treasury . The deficit peaked in fiscal year 2020 at $3.13 trillion, and declined to $1.7 trillion by the end of fiscal year 2023.

By Julia Ingram

• Presidential Debate
• Donald Trump

Arden Farhi is the senior White House producer at CBS News. He has covered several presidential campaigns and the Obama, Trump and Biden administrations. He also produces "The Takeout with Major Garrett."

More from CBS News

Poll: Trump gets edge over Biden nationally, across battlegrounds after debate

Concern mounts among lawmakers, donors over Biden's candidacy

Harris says "Joe Biden is our nominee" after calls for him to step aside

Biden vows to stay in presidential race as he seeks to reassure allies

Advertisement

Supported by

Biden Warns That Supreme Court’s Immunity Ruling Will Embolden Trump

The president, under scrutiny since his damaging debate appearance last week, did not stumble or falter during his brief remarks.

• Share full article

Supreme Court’s Immunity Decision Sets ‘Dangerous Precedent,’ Biden Says

President biden spoke after the supreme court’s ruling that former president donald j. trump is entitled to substantial immunity from prosecution on charges of trying to overturn the 2020 election..

No one, no one is above the law, not even the president of the United States. But today’s Supreme Court decision on presidential immunity, that fundamentally changed. For all, for all practical purposes, today’s decision almost certainly means that there are virtually no limits on what the president can do. This is a fundamentally new principle and it’s a dangerous precedent, because the power of the office will no longer be constrained by the law, even including the Supreme Court of the United States. The only limits will be self imposed by the president alone. Now, the American people will have to do what the courts should have been willing to do, but would not. The American people have to render a judgment about Donald Trump’s behavior. The American people must decide, do they want to entrust the president once again — the presidency — to Donald Trump now knowing he’ll be even more emboldened to do whatever he pleases whenever he wants to do it.

By Michael D. Shear

Reporting from Washington

President Biden warned on Monday that the Supreme Court’s decision on presidential immunity meant that there were “virtually no limits on what the president can do” and urged voters to prevent former President Donald J. Trump from returning to the White House freed from the constraints of the law.

“The American people must decide if they want to entrust the president once again — the presidency — to Donald Trump,” Mr. Biden said during brief remarks, “knowing he’ll be more emboldened to do whatever he pleases whenever he wants to do it.”

Mr. Biden’s response to Monday’s court ruling was his first public remarks since he spent the weekend hunkered down with family at Camp David. His disastrous debate performance in Atlanta last week has led some Democrats to call for him to drop out of the presidential race because of concerns about his age and mental fitness.

The president appeared ruddier than he did during the 90-minute debate, when many observed that he looked very pale. He did not stumble over his words on Monday or falter midsentence. But he was using a teleprompter for the remarks, which lasted about four and a half minutes.

Mr. Biden also did not respond to several shouted questions at the end of the remarks on Monday, including one asking whether he intended to drop out of the race.

The Supreme Court ruled on Monday that Mr. Trump has significant immunity against prosecution on charges of trying to overturn the 2020 election. Mr. Biden called that a “dangerous precedent” that fundamentally alters the longstanding belief in the United States that no one should be above the law.

We are having trouble retrieving the article content.

Please enable JavaScript in your browser settings.

Thank you for your patience while we verify access. If you are in Reader mode please exit and  log into  your Times account, or  subscribe  for all of The Times.

Thank you for your patience while we verify access.

Already a subscriber?  Log in .

Want all of The Times?  Subscribe .

U.S. President Joe Biden speaks to supporters at a debate night watch party after participating in the first presidential debate hosted by CNN in Atlanta, Georgia, U.S., June 27, 2024. REUTERS/Elizabeth Frantz

Biden's stumbles leave Democrats fearing for election - US Presidential debate as it happened

Our Standards: The Thomson Reuters Trust Principles. New Tab , opens new tab

Thomson Reuters

Live Page editor. A text and video journalist based in London, Stephen is a former Reuters bureau chief in Jerusalem. He was previously a foreign correspondent for The New York Times and The Times of London. He reported from the Balkans, Iraq, India, Afghanistan, New York and the UK. He is co-author of the book 'Hamas: The Islamic Resistance Movement’.

Mark Porter is a desk editor at Reuters, where he files a plethora of stories on numerous topics, from general news to business and political news. In his more than 20 years at Reuters, Porter has been on the initial teams for the Reuters Insider television project and the breaking news team, he started the entertainment blog and was the Reuters embedded editor at Yahoo. He has worked for almost 40 years as a journalist, with stints at the New York Times, TheStreet.com, Dow Jones and Knight-Ridder/Bridge News.

Rupam Jain reports on India's politics and policy. She has reported from Afghanistan, Iran, the MENA countries, Nepal and Bangladesh. Before joining Reuters, she worked at Agence France Presse (AFP) and The Indian Express. Rupam studied at the Columbia University and the Calcutta University.