Free Audio Transcriber
Turn speech into text with the Whisper model — running 100% in your browser.
Upload an audio file or record from your microphone, then hit Transcribe. On first use the AI model downloads once (then is cached for future visits) and all processing happens on your device — your audio is never sent to any server.
🔒 100% private — nothing is uploaded or stored.
All processing happens inside your browser using web-based AI. Your audio file never leaves your
device — it is never sent to our servers and nothing is stored anywhere. The transcript exists only
on your device until you copy or download it. The only download is the AI model itself (once, from
Hugging Face, then cached by your browser).
Drop an audio file here, or click to browse
MP3, WAV, M4A, OGG, FLAC, WEBM — anything your browser can decode
Powered by the open-source Whisper model (Apache-2.0) running via Transformers.js / ONNX Runtime Web. Model weights download from the Hugging Face Hub on first use and are cached by your browser.
