Fish Audio: Transcribe 1
fish-audio/transcribe-1- Modalities
- audio->transcription
- In / out price
- $100 / $0
- Context
- —
- Released
- Jul 29, 2026
- Knowledge cutoff
- —
per 1M
The playground sends chat/completions only. This model outputs Transcription, so a chat turn may not return what you expect.
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.
AudioTranscription
Supported parameters
This model does not publish a parameter list.