Free audio and video transcription in your browser

Turn audio or video into editable text with timestamps. Use a file up to 300 MiB and 20 minutes, a direct media link or your microphone. Review the transcript, then copy it or download it as TXT, JSON, SRT or VTT.

Try the English sampleNo account. No media upload.
  1. Choose media
  2. Check settings
  3. Transcribe
  4. Use your text

Choose a recording to get started. You can check its language before transcription.

Transcription runs in this browser

Try a short recording before your own file

Listen to a public English, Spanish or Arabic sample, load it into the tool, then compare your result with the dataset reference. These short read-speech clips do not represent noisy meetings or long recordings.

English sample

10.56 sec
Download audio
Compare the reference and the test outputDataset reference text

However, due to the slow communication channels, styles in the west could lag behind by 25 to 30 year.

Standard transcription · Whisper Tiny Q8 on WebAssembly

In the test, Whisper wrote “this little communication channels” where the reference says “the slow communication channels”.

Download the transcript from the test

Spanish sample

12.84 sec
Download audio
Dataset reference text

Se recomienda enfáticamente a los viajeros que se informen sobre cualquier riesgo de clima extremo en el área que visitan, dado que ello puede afectar sus planes de viaje.

The reference is a dataset transcript, not a promise of the tool's output.

Arabic sample

8.16 sec
Download audio
Dataset reference text

تشكلت في المحيط الأطلسي اليوم عاشر عاصفة مُسماة لموسم الأعاصير الأطلسية، العاصفة شبه الاستوائية جيري.

The reference is a dataset transcript, not a promise of the tool's output.

Sample files and browser test results

Sample sources and test details

Audio and reference: FLEURS contributors / Google, CC BY 4.0. Original recordings are unchanged. FLEURS · CC BY 4.0

Transcribe audio to text in your browser

Choose a recording in the file picker and select the language you hear. If this is your first run, leave the tab open while the speech model downloads. Whisper Web then reads the audio on your device. For a video, it listens to the audio track, so you can start with the original MP4 and skip the audio extraction step.

When the transcript appears, replay a passage and check names, numbers and unfamiliar terms against the recording. Keep the text as a starting point for interview notes, or use the timestamps to find a quote again. For captions, you can transcribe audio to text for SRT subtitles and review each cue before saving it. A plain text export works well when you only need the words.

  • Open an MP3, WAV, M4A or MP4 file that your browser can decode.
  • Use the standard workspace for one file up to 300 MiB and 20 minutes.
  • Your recording stays on this device. Export TXT for text or SRT and VTT for captions.

How does Whisper Web transcribe your recording?

  1. 01ImportFile, direct link or microphone
  2. 02Recognize locallyWhisper runs on your device
  3. 03ExportTXT, JSON, SRT or VTT

Which workflow fits your recording?

Choose a recording type for step-by-step help, or read a guide before deciding where to process the audio and which file to export.

Subtitle tools and guides

What stays on your device, and what still uses the network?

Your selected local media and completed transcript stay in this browser. The page, Whisper model and direct media URLs use the network; optional analytics connects only after you allow it.

  • No media upload

    The selected media is processed on your device and is not sent to Whisper Web servers.

  • Two compute options

    WebGPU can run faster; WebAssembly provides a broadly compatible fallback.

  • Edit and export locally

    Correct the text, copy it or export TXT, JSON, SRT or VTT.

How Whisper Web handles media, transcripts and network requests
Your questionWhat happens in Whisper Web
Does a selected file leave this device?No. The browser decodes and transcribes the selected local file on this device.
Where is the finished transcript saved?In this browser's IndexedDB when storage is available. If saving fails, export the current result before closing the page.
Why does the Whisper model use the network?The browser downloads the model you choose, then runs it on this device.
What loads when you open the page?The browser downloads the application code, fonts and other website files.
What happens when you paste a direct media URL?Your browser requests the media from its source host, so that host receives the request.
What do analytics services receive?Only after you allow analytics: registered public pages, sanitized sources and predefined usage categories. Product events exclude your media, filename and transcript text.

Questions about local transcription

Is Whisper Web the same as OpenAI Whisper?

Whisper Web at whisperwebfree.com is an independent browser app that runs OpenAI’s open-source Whisper speech recognition model on your device.

Is Whisper Web free and does it need an account?

Whisper Web is free to use. You can start transcribing and download the result without signing in.

How many recordings can I transcribe for free each day?

There is no daily recording limit for local transcription. Choose one file at a time. Each file in the standard workspace can be up to 20 minutes and 300 MiB.

Does Whisper Web keep a copy of my recording or transcript?

When you choose File or Microphone, your audio and transcript stay on your device. The transcript can be saved in this browser’s History. Delete the entry there after exporting any copy you want to keep. If you use Link, your browser contacts the host of that media.

Do I need to install anything to use Whisper Web in Chrome?

Open this page in Chrome and choose a recording. The first time you use a model, Chrome downloads it and caches it for later use. You can transcribe without installing a desktop app or extension.

Which formats are supported?

Whisper Web accepts common MP3, WAV, M4A, MP4 and WebM files, subject to your browser's decoding support.

Which languages can I transcribe?

The Audio language menu includes 99 languages, including English, Spanish, Arabic, Chinese, Hindi, French, German, Japanese and Portuguese. Choose the language spoken in the recording before you start.

Can I transcribe a voice memo on my phone?

Save the recording as a file first. On iPhone, open the memo, choose Share, then Save to Files. Select it here and try a short clip first. Playback and transcription depend on the codec your mobile browser can decode and the memory available.

Follow the voice memo guide
What if I need to transcribe a large file?

For longer recordings, use the large-file tool. It accepts up to one hour and 1 GiB per local file. For a two-hour interview, split at pauses into parts within both limits and export each transcript before closing the tab.

Transcribe a large file

Your privacy choices

Allow Google Analytics and Plausible to measure visits and tool usage? Optional analytics stays off until you agree. Your files and transcripts are not included in product events. The tools work either way. Privacy Policy