Speech to Text

Info

Powered by Whisper by OpenAI, running locally in your browser via Transformers.js by Hugging Face.
To keep the loading and processing down, we are using whisper tiny.en, which only supports English, and commonly makes mistakes.
Clients, please use Clio’s read for significantly more accurate and timely results, running server-side.

Warning

Using this app (adding an audio file and hitting generate) will download ~35MBs of AI onto your device!
It also uses a fair bit of processing power!

Drop audio file here

or click to browse

Supports: WAV, MP3, M4A, OGG, WebM, FLAC

Ready. Model will download (~41 MB) when you click Transcribe.

Transcript