Music Hall · room 6
Speech to Text
Transcribe audio and video to text with Whisper AI.
🔒 Processed in your browser · No upload · No sign-up
Drop an audio or video file here or click to browse
MP3, WAV, M4A, MP4, WebM… The AI model runs on your device.
Transcribe audio to text with Whisper — privately
This tool runs OpenAI's open-source Whisper speech recognition model directly in your browser using transformers.js (WebGPU when available, otherwise WebAssembly). It supports ~100 languages, can translate speech to English, and exports subtitles as SRT or VTT.
Is my audio uploaded?
No. Only the model files are downloaded (once, then cached). Your recording is decoded and transcribed locally.
How long does it take?
With WebGPU (recent Chrome / Edge) a few minutes of audio typically transcribe in under a minute. On CPU it can be several times slower — choose the Tiny model for speed, Small for accuracy.