FishAudioTTSConfig

Configuration for the FishAudioTTS provider.

Defined in: src/providers/tts/fishaudio/FishAudioTTS.ts:118

Configuration for the FishAudioTTS provider.

Remarks

Provide either apiKey (for direct API access) or proxyUrl (for server-side proxy). At least one must be set. If both are provided, proxyUrl takes precedence and the API key is not sent to the client.

The optional peer dependency @msgpack/msgpack must be installed — it is loaded lazily during initialize().

Example

// Direct API access
const config: FishAudioTTSConfig = {
  apiKey: 'fa_xxxxxxxxxxxx',
  referenceId: 'your-voice-id',
  model: 's2.1-pro',
  format: 'mp3',
};

// Via proxy server
const proxyConfig: FishAudioTTSConfig = {
  proxyUrl: 'http://localhost:3001/api/proxy/fishaudio',
  referenceId: 'your-voice-id',
};

See

FishAudioTTSModel - Available model generations.
FishAudioTTSFormat - Available audio format options.

Extends

TTSProviderConfig

Properties

Property	Type	Default value	Description	Overrides	Inherited from	Defined in
`apiKey?`	`string` \| () => `Promise`<`string`>	`undefined`	API key or authentication token for the provider. Remarks Can be a static string or an async factory function that returns a fresh token on each call. Use a factory for short-lived tokens (e.g. Deepgram JWTs) so each WebSocket connection gets a valid credential. For client-side usage, consider using a proxy server to keep API keys secure. The SDK provides Express, Next.js, and Node adapters for this purpose.	-	`TTSProviderConfig`.`apiKey`	src/core/types/providers.ts:71
`authType?`	`"token"` \| `"bearer"`	`Provider-specific (typically 'token' for Deepgram, ignored for REST providers)`	Authentication type for providers that support multiple auth mechanisms. Remarks Controls how the `apiKey` is sent to the provider: - `'token'` — WebSocket subprotocol `['token', apiKey]` or header `Authorization: Token <key>`. This is the default for Deepgram providers. - `'bearer'` — WebSocket subprotocol `['bearer', token]` or header `Authorization: Bearer <token>`. Use this for OAuth tokens or providers that expect Bearer auth. REST/SDK providers (Anthropic, OpenAI) handle auth through their SDK constructors and ignore this field.	-	`TTSProviderConfig`.`authType`	src/core/types/providers.ts:115
`chunkLength?`	`number`	`300` (server-side)	Maximum characters per internal synthesis chunk (100-300).	-	-	src/providers/tts/fishaudio/FishAudioTTS.ts:164
`debug?`	`boolean`	`false`	Whether to enable debug logging for this provider. Remarks When `true`, the provider emits detailed internal logs. This is separate from the SDK-level LoggingConfig.	-	`TTSProviderConfig`.`debug`	src/core/types/providers.ts:126
`endpoint?`	`string`	`undefined`	Custom endpoint URL to override the provider’s default API endpoint. Remarks Useful for self-hosted instances, proxy servers, or development environments.	-	`TTSProviderConfig`.`endpoint`	src/core/types/providers.ts:79
`format?`	`FishAudioTTSFormat`	`'mp3'`	The audio output format. See FishAudioTTSFormat	-	-	src/providers/tts/fishaudio/FishAudioTTS.ts:150
`latency?`	`FishAudioTTSLatency`	`'normal'` (server-side)	Latency mode trading stability for time-to-first-audio. See FishAudioTTSLatency	-	-	src/providers/tts/fishaudio/FishAudioTTS.ts:179
`maxRetries?`	`number`	`3`	Maximum number of retries for failed API requests.	-	-	src/providers/tts/fishaudio/FishAudioTTS.ts:212
`model?`	`FishAudioTTSModel`	`'s2.1-pro-free'`	The TTS model generation, sent as the `model` HTTP header. Remarks Use `'s2.1-pro'` in production; `'s2.1-pro-free'` (the default, matching the API’s own default) is a free tier for testing and development. See FishAudioTTSModel	`TTSProviderConfig`.`model`	-	src/providers/tts/fishaudio/FishAudioTTS.ts:142
`mp3Bitrate?`	`64` \| `128` \| `192`	`128` (server-side)	Bitrate for `mp3` output, in kbps.	-	-	src/providers/tts/fishaudio/FishAudioTTS.ts:157
`normalize?`	`boolean`	`true` (server-side)	Whether to normalize numbers, dates, and other text before synthesis.	-	-	src/providers/tts/fishaudio/FishAudioTTS.ts:171
`outputFormat?`	`string`	`undefined`	Output audio format identifier. Remarks Provider-specific format string (e.g., `'linear16'`, `'mp3'`, `'opus'`).	-	`TTSProviderConfig`.`outputFormat`	src/core/types/providers.ts:1190
`pitch?`	`number`	`undefined`	Pitch adjustment in semitones. Remarks Values from -20 to +20 semitones. Not all providers support pitch adjustment.	-	`TTSProviderConfig`.`pitch`	src/core/types/providers.ts:1182
`proxyUrl?`	`string`	`undefined`	URL of a CompositeVoice proxy server endpoint for this provider. Remarks When set, requests are routed through the proxy which injects the real API key server-side. This keeps API keys out of the browser. For WebSocket providers the HTTP URL is automatically converted to `ws(s)://`. At least one of `apiKey` or `proxyUrl` must be set for providers that require authentication (all except NativeSTT, NativeTTS, and WebLLM). Example `proxyUrl: 'http://localhost:3000/api/proxy/deepgram'`	-	`TTSProviderConfig`.`proxyUrl`	src/core/types/providers.ts:97
`rate?`	`number`	`undefined`	Speech rate multiplier. Remarks Values from 0.25 (quarter speed) to 4.0 (quadruple speed), where 1.0 is normal speed. Not all providers support rate adjustment.	-	`TTSProviderConfig`.`rate`	src/core/types/providers.ts:1174
`referenceId?`	`string`	`undefined` (model default voice)	The voice model to synthesize with, from Fish Audio’s voice catalog (or a voice you created). Remarks Sent as `reference_id` in the request body. When omitted, the model’s default voice is used — or provide inline references for instant voice cloning.	-	-	src/providers/tts/fishaudio/FishAudioTTS.ts:130
`references?`	`FishAudioReference`[]	`undefined` (no cloning; uses `referenceId` or model default)	Inline reference audio samples for instant voice cloning. Remarks Binary reference audio is the reason this provider speaks msgpack — the JSON encoding cannot carry raw bytes. See FishAudioReference	-	-	src/providers/tts/fishaudio/FishAudioTTS.ts:205
`sampleRate?`	`number`	`undefined`	Sample rate for the output audio in Hz. Remarks Common values are 16000, 24000, and 48000. Must match the format capabilities of the chosen voice and model.	-	`TTSProviderConfig`.`sampleRate`	src/core/types/providers.ts:1199
`speed?`	`number`	`undefined` (server default, 1.0)	Speech speed multiplier, sent as `prosody.speed` (0.5-2.0).	-	-	src/providers/tts/fishaudio/FishAudioTTS.ts:186
`timeout?`	`number`	`undefined`	Request timeout in milliseconds. Remarks Applies to HTTP requests (REST providers) and connection establishment (WebSocket providers). Set to `0` for no timeout.	-	`TTSProviderConfig`.`timeout`	src/core/types/providers.ts:135
`voice?`	`string`	`undefined`	Voice ID or name to use for synthesis. Remarks Provider-specific voice identifier. For example, Deepgram uses identifiers like `'aura-asteria-en'`, while ElevenLabs uses voice IDs.	-	`TTSProviderConfig`.`voice`	src/core/types/providers.ts:1157
`volume?`	`number`	`undefined` (server default, 0)	Volume adjustment, sent as `prosody.volume`.	-	-	src/providers/tts/fishaudio/FishAudioTTS.ts:193