ElevenLabsSTTConfig

Configuration options for the ElevenLabs STT provider.

Defined in: src/providers/stt/elevenlabs/ElevenLabsSTT.ts:85

Configuration options for the ElevenLabs STT provider.

Remarks

Extends STTProviderConfig with ElevenLabs-specific settings. You must provide either apiKey / token (for direct browser-to-ElevenLabs connections) or proxyUrl (for a server-side proxy that injects the API key). If proxyUrl is provided, it takes precedence.

Example

// Direct connection (API key exposed to browser -- development only)
const config: ElevenLabsSTTConfig = {
  apiKey: 'el-xxxxxxxxxxxx',
  model: 'scribe_v2_realtime',
  commitStrategy: 'vad',
};

// Proxy connection (recommended for production)
const config: ElevenLabsSTTConfig = {
  proxyUrl: 'http://localhost:3001/api/proxy/elevenlabs',
  audioFormat: 'pcm_16000',
  includeTimestamps: true,
};

See

ElevenLabsSTTModel - Available model options.
ElevenLabsSTTAudioFormat - Available audio format options.

Extends

STTProviderConfig

Properties

Property	Type	Default value	Description	Overrides	Inherited from	Defined in
`apiKey?`	`string`	`undefined`	ElevenLabs API key for direct authentication. Required when connecting directly to ElevenLabs without a proxy.	`STTProviderConfig`.`apiKey`	-	src/providers/stt/elevenlabs/ElevenLabsSTT.ts:90
`audioFormat?`	`ElevenLabsSTTAudioFormat`	`undefined`	Audio encoding format sent to the API. Default `'pcm_16000'`	-	-	src/providers/stt/elevenlabs/ElevenLabsSTT.ts:122
`commitStrategy?`	`"vad"` \| `"manual"`	`undefined`	Strategy for committing transcription segments. - `'vad'` — Voice Activity Detection automatically commits when silence is detected - `'manual'` — Application controls when to commit via explicit signals Default `'vad'`	-	-	src/providers/stt/elevenlabs/ElevenLabsSTT.ts:116
`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.	-	`STTProviderConfig`.`debug`	src/core/types/providers.ts:86
`enableLogging?`	`boolean`	`undefined`	Whether to enable logging on the ElevenLabs side. When `false`, enables zero-retention mode where no audio or transcripts are stored by ElevenLabs.	-	-	src/providers/stt/elevenlabs/ElevenLabsSTT.ts:171
`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.	-	`STTProviderConfig`.`endpoint`	src/core/types/providers.ts:75
`includeLanguageDetection?`	`boolean`	`undefined`	Whether to include automatic language detection in results.	-	-	src/providers/stt/elevenlabs/ElevenLabsSTT.ts:157
`includeTimestamps?`	`boolean`	`undefined`	Whether to include word-level timestamps in transcription results. Default `false`	-	-	src/providers/stt/elevenlabs/ElevenLabsSTT.ts:152
`interimResults?`	`boolean`	`undefined`	Whether to enable interim (partial) transcription results. Remarks When `true`, the provider emits results as the user speaks, before the utterance is complete. Only applicable to live/WebSocket providers.	-	`STTProviderConfig`.`interimResults`	src/core/types/providers.ts:352
`keywords?`	`string`[]	`undefined`	Custom vocabulary or keyword phrases to boost recognition accuracy. Remarks Useful for domain-specific terminology, product names, or proper nouns that the model might not recognize well by default.	-	`STTProviderConfig`.`keywords`	src/core/types/providers.ts:366
`language?`	`string`	`undefined`	Language code for transcription. Remarks Uses BCP 47 language tags (e.g., `'en-US'`, `'es-ES'`, `'fr-FR'`). The supported languages depend on the provider and model.	-	`STTProviderConfig`.`language`	src/core/types/providers.ts:335
`minSilenceDurationMs?`	`number`	`undefined`	Minimum silence duration in milliseconds before a speech segment ends.	-	-	src/providers/stt/elevenlabs/ElevenLabsSTT.ts:146
`minSpeechDurationMs?`	`number`	`undefined`	Minimum speech duration in milliseconds before it is considered valid. Helps filter out very short noise bursts.	-	-	src/providers/stt/elevenlabs/ElevenLabsSTT.ts:141
`model?`	`ElevenLabsSTTModel`	`undefined`	STT model to use for transcription. Default `'scribe_v2_realtime'`	`STTProviderConfig`.`model`	-	src/providers/stt/elevenlabs/ElevenLabsSTT.ts:108
`previousText?`	`string`	`undefined`	Previous text context to improve transcription accuracy. Useful for maintaining context across sessions. Should be kept short (approximately 50 characters or less).	-	-	src/providers/stt/elevenlabs/ElevenLabsSTT.ts:164
`proxyUrl?`	`string`	`undefined`	URL of the CompositeVoice proxy server’s ElevenLabs endpoint. Example: `'http://localhost:3000/api/proxy/elevenlabs'`	-	-	src/providers/stt/elevenlabs/ElevenLabsSTT.ts:96
`punctuation?`	`boolean`	`undefined`	Whether to enable automatic punctuation in transcription results.	-	`STTProviderConfig`.`punctuation`	src/core/types/providers.ts:357
`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.	-	`STTProviderConfig`.`timeout`	src/core/types/providers.ts:95
`token?`	`string`	`undefined`	Temporary authentication token for WebSocket connections. Alternative to `apiKey` for short-lived browser sessions.	-	-	src/providers/stt/elevenlabs/ElevenLabsSTT.ts:102
`vadSilenceThresholdSecs?`	`number`	`undefined`	Duration of silence (in seconds) before VAD considers speech ended. Only applies when `commitStrategy` is `'vad'`.	-	-	src/providers/stt/elevenlabs/ElevenLabsSTT.ts:128
`vadThreshold?`	`number`	`undefined`	VAD sensitivity threshold (0.0 to 1.0). Higher values require louder speech to trigger detection. Only applies when `commitStrategy` is `'vad'`.	-	-	src/providers/stt/elevenlabs/ElevenLabsSTT.ts:135