Transcribe speech

Transcribe audio to text in multiple languages.

Our pick: incredibly-fast-whisper

For most needs, use incredibly-fast-whisper. It really is fast (10x quicker than original Whisper), cheap, accurate, and supports tons of languages.

For speaker labels: whisper-diarization

Need to label speakers or get word-level timestamps? whisper-diarization has you covered. Pricier than incredibly-fast-whisper but worth it for the extra features.

For translation: seamless_communication

To translate speech between languages, seamless_communication is your friend. Go from Spanish audio to German text or French speech with ease.