Models
One name per model, however many providers serve it.
Fish Audio: Drama 3
Accepts- Text
Creates- Audio
Drama 3 is a text-to-speech model from Fish Audio built for directed voice performances.
fish-audio/drama-3Oct 13, 2026MP3 · WAV3,604 Toman per 1,000 charactersFish Audio: Transcribe 1 Pro
Accepts- Audio
Creates- Text
Transcribe 1 Pro is a speech-to-text model from Fish Audio tuned for interviews, meetings, and podcasts.
fish-audio/transcribe-1-proSep 24, 2026With segment and word times2,162 Toman a minute of audioFish Audio: Transcribe 1
Accepts- Audio
Creates- Text
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.
fish-audio/transcribe-1Jul 29, 2026With segment and word times2,162 Toman a minute of audioFish Audio: S1
Accepts- Text
Creates- Audio
S1 is a multilingual text-to-speech model from Fish Audio.
fish-audio/s1Jul 29, 2026MP3 · WAV5,406 Toman per 1,000 charactersFish Audio: S2 Pro
Accepts- Text
Creates- Audio
S2 Pro is a multilingual text-to-speech model from Fish Audio. It is suited for expressive narration and multi-speaker dialogue, with natural-language controls for speaking style and emotion.
fish-audio/s2-proJul 29, 2026MP3 · WAV5,406 Toman per 1,000 charactersFish Audio: S2.1 Pro Free (free)
FreeAccepts- Text
Creates- Audio
S2.1 Pro Free is the no-cost variant of Fish Audio S2.1 Pro, intended for testing, prototyping, and low-volume applications.
fish-audio/s2.1-pro-free:freeJul 29, 2026MP3 · WAVFreeFish Audio: S2.1 Pro
Accepts- Text
Creates- Audio
S2.1 Pro is a production-oriented text-to-speech model from Fish Audio.
fish-audio/s2.1-proJul 29, 2026MP3 · WAV5,406 Toman per 1,000 characters
7 of 581 models · Catalog updated 3 hours ago. · Free plan prices, in Toman at today's rate. Plans and prices

