English sample
10.56 secDataset reference text
However, due to the slow communication channels, styles in the west could lag behind by 25 to 30 year.
The reference is a dataset transcript, not a promise of the tool's output.Free audio and video transcription in your browser
Whisper Web turns audio and video into editable text with timestamps in your browser. Choose a file up to 300 MiB and 20 minutes, paste a direct media link the browser can read or record with your microphone. The browser needs to download the speech model first. Review the text, then export TXT, JSON, SRT or VTT.
No account. No media upload.- Choose media
- Check settings
- Transcribe
- Use your text
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.
Spanish sample
12.84 secDataset 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 secDataset 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.How does Whisper Web transcribe your recording?
- 01ImportFile, direct link or microphone
- 02Recognize locallyWhisper runs on your device
- 03ExportTXT, JSON, SRT or VTT
Only need the audio, not a transcript?
Extract the main audio track from an MP4, MOV or WebM video and download it as an MP3 without uploading the video. MP4 to MP3 conversion guide
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.
Use cases
View all use casesGuides
View all guidesSubtitle 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.
| Your question | What 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
Does my file leave this device?
No. In local mode, the browser reads and decodes it in memory.
Why is the first transcription slower?
The selected Whisper model downloads once and is then cached by your browser.
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.
What if I need to transcribe a large file?
Use the large-file page for a local audio or video file up to 1 GiB and 1 hour. Keep this tab open: a long job can warm the device and take time. A reference estimate appears after processing begins.
Transcribe a large file
