AI Speech to Text
Transcribe audio to text instantly with AI. 100% free, runs locally in your browser - your audio never leaves your device.
100% Private
Processed locally
Fast Processing
Results in seconds
AI Powered
Whisper model
Upload an audio file
Drag and drop or click to browse
MP3, WAV, M4A, OGG, WebM up to 25MB
Powered by Whisper and Transformers.js
Frequently Asked Questions
Is my audio uploaded anywhere?
No. Transcription runs entirely in your browser using Whisper via Transformers.js. The only network request is downloading the model itself from Hugging Face — your audio file never leaves your device.
What languages are supported?
English, Chinese, Japanese, Korean, Spanish, French, German, Russian, Portuguese, Italian, Hindi, and Arabic. You must select the spoken language before transcribing — Whisper defaults to English if none is chosen.
Why does Chinese transcription come out in Traditional characters?
Whisper's Chinese output leans Traditional regardless of the actual accent spoken. Use the 简体/繁體 toggle above the transcript to switch between Simplified and Traditional after transcription.
What are the file limits?
MP3, WAV, M4A, OGG, or WebM files up to 25MB and 10 minutes long.