fish-audio/drama-3-20261013
Drama 3 is a text-to-speech model from Fish Audio built for directed voice performances. You write the direction in plain language in square brackets before a line, such as `[nervous, barely holding it together]`, and can add sounds and pauses inline or change the delivery of spe
- Context window
- 0
- Input modalities
- text
- Output modalities
- speech
- Capabilities
- audioOutput, speechOutput
fish-audio/s1-20260729
S1 is a multilingual text-to-speech model from Fish Audio. It is suited for voice applications that need broad emotional expression, using parenthetical controls to guide speaking style across its supported languages.
- Context window
- 0
- Input modalities
- text
- Output modalities
- speech
- Capabilities
- speechOutput
fish-audio/s2.1-pro-20260729
S2.1 Pro is a production-oriented text-to-speech model from Fish Audio. It is suited for multilingual voice applications, expressive narration, and dialogue synthesis, with open-ended natural-language controls for speaking style and emotion.
- Context window
- 0
- Input modalities
- text
- Output modalities
- speech
- Capabilities
- audioOutput, speechOutput
fish-audio/s2.1-pro-free-20260729
S2.1 Pro Free is the no-cost variant of Fish Audio S2.1 Pro, intended for testing, prototyping, and low-volume applications. It provides the same synthesis capabilities without production latency or availability guarantees.
- Context window
- 0
- Input modalities
- text
- Output modalities
- speech
- Capabilities
- speechOutput
fish-audio/s2-pro-20260729
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.
- Context window
- 0
- Input modalities
- text
- Output modalities
- speech
- Capabilities
- audioOutput, speechOutput
fish-audio/transcribe-1-20260729
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.
- Context window
- 0
- Input modalities
- audio
- Output modalities
- transcription
- Capabilities
- audioInput, transcription
fish-audio/transcribe-1-pro-20260924
Transcribe 1 Pro is a speech-to-text model from Fish Audio tuned for interviews, meetings, and podcasts. It labels speakers with inline `speaker` markers, preserves emotion and vocal-event cues such as `[laughter]`, detects language automatically, and can return timestamped word-
- Context window
- 0
- Input modalities
- audio
- Output modalities
- transcription
- Capabilities
- audioInput
vercelAIGatewayCatalog/fish-audio/s1
Fish Audio S1 is trained on over 2 million hours of audio with online RLHF (GRPO). It achieves 0.8% WER and 0.4% CER on Seed TTS Eval. S1 supports open-domain emotion, tone, and special effect markers.
- Input modalities
- text
- Output modalities
- audio
- Capabilities
- audioOutput, speechOutput