Fish Audio: Transcribe 1
- by fish-audio
- fish-audio/transcribe-1
Transcribe 1 is a speech-to-text model from Fish Audio. It is suited for audio transcription with automatic language detection and can return timestamped word-level segments when alignment details are requested.
What the numbers mean
- Input price$100 per million tokens
- What you pay for everything the model reads. A 1,000-word prompt costs about $0.13.
- Output priceFree
- What you pay for everything the model writes. Output usually costs more than input. A 500-word answer costs nothing.
- Modalitiesaudio in, transcription out
- The kinds of content it accepts and the kinds it produces. A model that takes images in can read a screenshot; one that only puts text out cannot draw.