Transcribe any audio using Whisper AI — runs entirely in your browser. Private, free, no sign-up, no upload to servers.
🎵
Drop audio here or browse
MP3 · WAV · M4A · OGG · FLAC · WebM · max 25 MB
⏱ 0:00
Language
🤖 Uses Whisper Tiny AI model (~40 MB, downloaded once and cached). All processing runs in your browser — your audio never leaves your device.
How to use
1
Upload an audio file (MP3, WAV, M4A…) or record directly from your mic.
2
Select a language or leave on Auto-detect. Then click Transcribe.
3
The first run downloads the Whisper AI model (~40 MB). After that it's instant — even offline.
4
Copy or download the transcript. Nothing is sent to any server.
Frequently Asked Questions
Is this free?
Yes — completely free, no sign-up, no limits.
Is my audio private?
Yes. Your audio never leaves your device. The Whisper AI model runs entirely inside your browser using WebAssembly — no server, no tracking.
What audio formats are supported?
Any format your browser can decode: MP3, WAV, M4A, OGG, FLAC, WebM. If it plays in your browser, it can be transcribed.
What languages does it support?
Whisper supports 99 languages including English, Chinese, Japanese, Korean, Spanish, French, German, Portuguese, Indonesian, Arabic, Russian and more. Use Auto-detect or pick a language for better accuracy.
Why does it take time on first use?
The Whisper AI model (~40 MB) is downloaded once from a CDN and cached by your browser. After the first use, transcription starts immediately — even offline.
Is there a file size limit?
25 MB per file. For longer recordings, consider splitting the audio first. Processing time depends on your device — modern laptops handle 5 minutes of audio in about 30 seconds.
