Loading utilities...
Convert speech to text using OpenAI's Whisper model. Supports 99 languages. All processing happens in your browser for maximum privacy.
First load tip: Models are downloaded once and cached by your browser. Tiny/Base models load quickly (~5-15s), while Small models take longer (~30-60s).
Drop audio file here or click to browse
Supports MP3, WAV, OGG, FLAC, M4A, WebM (up to 100MB)
🚀 Large file support (100-500MB) coming soon!
100% Browser Processing: All transcription happens in your browser for maximum privacy. Files under 100MB are supported. Large file support (100-500MB) coming soon!
Performance: First load downloads the model (~40-245MB). Subsequent browser uses are instant. Server processing is faster for large files.
Languages: Multilingual models support 99 languages including English, Spanish, French, German, Chinese, Japanese, Arabic, and many more.
Coming Soon: Server processing for large files (100-500MB) will be available in a future update!