FishAudioTTS
Streaming text-to-speech with Fish Audio S2 voices, using your own Fish Audio key. Expressive speech in 80+ languages with [bracket] emotion cues and cloned voices. Authenticates with FISH_API_KEY from your environment, or an explicitapi_key.
Fields
str
default:"UNSET"
TTS model: “s2.1-pro”, “s2.1-pro-free” (same model, no latency guarantees), “s2-pro” or “drama-3”. “s1” is deprecated. Defaults to ‘s2.1-pro’.
str
default:"UNSET"
Fish Audio voice model ID, from the voice library or your own clones. Defaults to ‘933563129e564b19a115bedd57b7406a’.
Literal['low', 'balanced', 'normal']
default:"UNSET"
Latency against stability: “low” for the lowest latency, “balanced” for slightly steadier output, “normal” for the most stable output at about a second more to first audio. Defaults to ‘low’.
float | None
default:"UNSET"
Expressiveness from 0 to 1. Higher is more varied, lower is more consistent. Leave unset for Fish Audio’s default. Defaults to None (not set).
float | None
default:"UNSET"
Nucleus-sampling diversity from 0 to 1. Leave unset for Fish Audio’s default. Defaults to None (not set).
Mapping[str, Any] | None
default:"UNSET"
Delivery controls such as {“speed”: 1.1, “volume”: 0, “normalize_loudness”: true}. Speed 0.5 to 2.0, volume in dB from -20 to 20; only the keys you set are sent. Defaults to None (not set).
bool | None
default:"UNSET"
Spell out numbers, dates and units as words before synthesis. Leave unset for Fish Audio’s default (on). Defaults to None (not set).
int | None
default:"UNSET"
Text segment size from 100 to 300 characters. Leave unset for Fish Audio’s default. Defaults to None (not set).
str | None
default:"UNSET"
Language tag of the text, e.g. “en” or “es-MX”, used only to spell out numbers and dates. Leave unset to detect it. Defaults to None (not set).
str
default:"UNSET"
WebSocket endpoint of Fish Audio streaming text-to-speech. Change only for a proxy. Defaults to ‘wss://api.fish.audio/v1/tts/live’.