ElevenLabsAgent
ElevenLabs Conversational AI agent — covers STT + LLM + TTS in a single WebSocket.
Defined in: src/providers/agent/elevenlabs/ElevenLabsAgent.ts:82
ElevenLabs Conversational AI agent — covers STT + LLM + TTS in a single WebSocket.
See
- ElevenLabsAgentConfig for configuration options
- BaseAgentProvider for the shared agent provider base class
- ElevenLabsAgentEvent for events emitted via onAgentEvent
Extends
Constructors
Constructor
new ElevenLabsAgent(config?, logger?): ElevenLabsAgent;
Defined in: src/providers/agent/elevenlabs/ElevenLabsAgent.ts:107
Parameters
| Parameter | Type |
|---|---|
config | ElevenLabsAgentConfig |
logger? | Logger |
Returns
ElevenLabsAgent
Overrides
Properties
| Property | Modifier | Type | Default value | Description | Overrides | Inherited from | Defined in |
|---|---|---|---|---|---|---|---|
audioCallback? | protected | (chunk) => void | undefined | - | - | BaseAgentProvider.audioCallback | src/providers/base/BaseAgentProvider.ts:98 |
config | readonly | ElevenLabsAgentConfig & { model: string; } | undefined | Merged config satisfying STT + LLM + TTS duck-type checks. | BaseAgentProvider.config | - | src/providers/agent/elevenlabs/ElevenLabsAgent.ts:83 |
initialized | protected | boolean | false | Tracks whether initialize has completed successfully. | - | BaseAgentProvider.initialized | src/providers/base/BaseProvider.ts:97 |
logger | protected | Logger | undefined | Scoped logger instance for this provider. | - | BaseAgentProvider.logger | src/providers/base/BaseProvider.ts:94 |
metadataCallback? | protected | (metadata) => void | undefined | - | - | BaseAgentProvider.metadataCallback | src/providers/base/BaseAgentProvider.ts:99 |
preferredInputSampleRate | readonly | 16000 | DEFAULT_INPUT_SAMPLE_RATE | The ConvAI default input rate — what an auto-created mic should use. | BaseAgentProvider.preferredInputSampleRate | - | src/providers/agent/elevenlabs/ElevenLabsAgent.ts:100 |
roles | readonly | readonly ProviderRole[] | [] | Pipeline roles this provider covers. Remarks Subclasses override this to declare which pipeline stages they handle. For example, BaseSTTProvider sets ['stt'], while NativeSTT overrides to ['input', 'stt'] because it manages its own microphone. See ProviderRole for the possible role values | - | BaseAgentProvider.roles | src/providers/base/BaseAgentProvider.ts:90 |
transcriptionCallback? | protected | (result) => void | undefined | - | - | BaseAgentProvider.transcriptionCallback | src/providers/base/BaseAgentProvider.ts:97 |
type | readonly | ProviderType | undefined | Communication transport this provider uses ('rest' or 'websocket'). | - | BaseAgentProvider.type | src/providers/base/BaseProvider.ts:74 |
Accessors
isProxyMode
Get Signature
get protected isProxyMode(): boolean;
Defined in: src/providers/base/BaseProvider.ts:286
Whether the provider is in proxy mode.
Returns
boolean
true when proxyUrl is set.
Inherited from
Methods
assertAuth()
protected assertAuth(): void;
Defined in: src/providers/base/BaseProvider.ts:272
Validate that auth is configured (either apiKey or proxyUrl).
Returns
void
Remarks
Call this in onInitialize() for any provider that requires external authentication. Native providers (NativeSTT, NativeTTS) and in-browser providers (WebLLM) should NOT call this method.
Throws
ProviderInitializationError Thrown when neither apiKey nor proxyUrl is set.
Inherited from
assertReady()
protected assertReady(): void;
Defined in: src/providers/base/BaseProvider.ts:255
Guard that throws if the provider has not been initialized.
Returns
void
Remarks
Call at the start of any method that requires the provider to be ready.
Throws
Error Thrown with a descriptive message when initialized is false.
Inherited from
cleanupPendingState()
protected cleanupPendingState(): void;
Defined in: src/providers/base/BaseAgentProvider.ts:611
Clean up all pending promises and timers. Call from your onDispose() or connection close handler.
Returns
void
Inherited from
BaseAgentProvider.cleanupPendingState
clearBufferedAssistantText()
protected clearBufferedAssistantText(): void;
Defined in: src/providers/base/BaseAgentProvider.ts:526
Discard assistant text buffered for a response that is being abandoned.
Returns
void
Remarks
Call this when the user starts a new utterance (barge-in, or the provider’s “user started speaking” event). Text left in the buffer by a response nobody consumed would otherwise be handed to the next turn’s iterator as if it were that turn’s answer.
Inherited from
BaseAgentProvider.clearBufferedAssistantText
configureInputFormat()
configureInputFormat(metadata): void;
Defined in: src/providers/agent/elevenlabs/ElevenLabsAgent.ts:282
Record the input provider’s capture rate.
Parameters
| Parameter | Type | Description |
|---|---|---|
metadata | AudioMetadata | The input provider’s audio format. |
Returns
void
Remarks
The input format belongs to the agent’s dashboard configuration, not to anything this client can negotiate, so a mismatch can only be reported — see the user_input_audio_format check in the initiation metadata.
Overrides
BaseAgentProvider.configureInputFormat
connect()
connect(): Promise<void>;
Defined in: src/providers/agent/elevenlabs/ElevenLabsAgent.ts:171
Open the WebSocket and complete the conversation initiation handshake.
Returns
Promise<void>
Remarks
The connection follows a 2-step handshake:
- Open → initiation data — a WebSocket is opened to the signed URL, the proxy, or
wss://api.elevenlabs.io/v1/convai/conversation(withagent_id, plusxi-api-keyin direct mode with an API key). On open, the client sendsconversation_initiation_client_datawith any configured overrides and dynamic variables. - conversation_initiation_metadata — the server announces the conversation ID and audio formats. The output format is parsed and forwarded to the output provider; the connection is now ready.
The handshake must complete within the configured timeout (default 10 s, override via config.timeout).
Idempotent / piggyback behavior: returns immediately when already connected; piggybacks on an in-flight handshake instead of opening a second socket.
Throws
If the handshake does not complete within the timeout.
Throws
If the WebSocket errors or closes before the handshake finishes.
Overrides
disconnect()
disconnect(): Promise<void>;
Defined in: src/providers/base/BaseAgentProvider.ts:246
No-op — the agent connection is persistent.
Returns
Promise<void>
Remarks
The orchestrator calls stt.disconnect() / tts.disconnect() during turn-taking and barge-in. For agent providers, the connection must not be torn down between turns. The real close happens in dispose().
Inherited from
dispose()
dispose(): Promise<void>;
Defined in: src/providers/base/BaseProvider.ts:154
Clean up resources and dispose of the provider.
Returns
Promise<void>
Remarks
Delegates to the subclass hook onDispose and resets the initialized flag. If the provider is not initialized, the call is a no-op.
Throws
Re-throws any error raised by onDispose.
Inherited from
emitAssistantText()
protected emitAssistantText(text): void;
Defined in: src/providers/base/BaseAgentProvider.ts:507
Deliver the assistant’s response text. Resolves the pending generateFromMessages iterator.
Parameters
| Parameter | Type | Description |
|---|---|---|
text | string | The assistant’s response text received from the agent server. |
Returns
void
Remarks
When no iterator has registered yet — the orchestrator’s STT → LLM flow runs asynchronously after emitUserTranscription, so a fast agent can respond first — the text is buffered and consumed by the next iterator for this turn instead of being dropped.
Inherited from
BaseAgentProvider.emitAssistantText
emitAudioChunk()
protected emitAudioChunk(data): void;
Defined in: src/providers/base/BaseAgentProvider.ts:545
Forward a binary audio chunk to the output provider.
Parameters
| Parameter | Type | Description |
|---|---|---|
data | ArrayBuffer | Raw audio bytes to deliver via the registered audioCallback. Zero-length buffers are silently dropped. |
Returns
void
Remarks
The audio format is re-asserted before every chunk. Barge-in tears down playback via BrowserAudioOutput.stop(), which clears the player’s metadata, and nothing else replays it — without this, raw PCM arriving after the first barge-in has no format to decode with and the rest of the session is silent. emitOutputMetadata is a cheap field assignment on the output side, so re-asserting per chunk costs nothing and removes the race between “playback stopped” and “next chunk”.
Inherited from
BaseAgentProvider.emitAudioChunk
emitOutputMetadata()
protected emitOutputMetadata(): void;
Defined in: src/providers/agent/elevenlabs/ElevenLabsAgent.ts:263
Emit audio format metadata so the output provider can decode PCM.
Returns
void
Nothing — metadata is delivered via the registered metadataCallback.
Remarks
Called after the handshake and again before every audio chunk (because BrowserAudioOutput.stop() clears metadata during barge-in). Must therefore be cheap and side-effect free — subclasses should do nothing but call this.metadataCallback?.(metadata).
Overrides
BaseAgentProvider.emitOutputMetadata
emitUserTranscription()
protected emitUserTranscription(text): void;
Defined in: src/providers/base/BaseAgentProvider.ts:473
Emit a user transcription. Creates a new per-turn audio promise and triggers the orchestrator’s STT -> LLM flow.
Parameters
| Parameter | Type | Description |
|---|---|---|
text | string | The transcribed user speech to forward to the orchestrator’s transcription callback. |
Returns
void
Inherited from
BaseAgentProvider.emitUserTranscription
finalize()
finalize(): Promise<void>;
Defined in: src/providers/base/BaseAgentProvider.ts:425
Wait for the agent to finish sending all audio for the current turn.
Returns
Promise<void>
A promise that resolves when the current turn’s audio is complete or the 30 s timeout elapses.
Remarks
Resolves when the subclass calls markAudioDone, or after a 30-second safety timeout — whichever comes first. The timeout prevents the orchestrator from hanging indefinitely if the agent never signals completion.
Inherited from
generate()
generate(prompt, options?): Promise<AsyncIterable<string, any, any>>;
Defined in: src/providers/base/BaseAgentProvider.ts:317
Generate a response from a single user prompt.
Parameters
| Parameter | Type | Description |
|---|---|---|
prompt | string | The user’s text input. |
options? | LLMGenerationOptions | Optional generation overrides (only signal is meaningful for agent providers). |
Returns
Promise<AsyncIterable<string, any, any>>
An async iterable that yields the assistant’s response as a single text chunk.
Remarks
Wraps the prompt in a user message and delegates to generateFromMessages.
Throws
AbortError if the supplied options.signal is aborted before the server responds.
Inherited from
generateFromMessages()
generateFromMessages(_messages, _options?): Promise<AsyncIterable<string, any, any>>;
Defined in: src/providers/base/BaseAgentProvider.ts:349
Returns an async iterable that yields the assistant’s response text.
Parameters
| Parameter | Type | Description |
|---|---|---|
_messages | LLMMessage[] | Conversation messages (ignored — the agent server maintains its own history). |
_options? | LLMGenerationOptions | Optional generation overrides. Only signal is observed to support abort. |
Returns
Promise<AsyncIterable<string, any, any>>
An async iterable that yields the assistant’s response as a single text chunk.
Remarks
Agent APIs manage their own conversation context. This method does NOT re-send the message history — the server already has it. Instead, it returns an iterable that blocks until the server sends the assistant’s response text, then yields it as a single chunk.
The returned iterator resolves when the subclass calls emitAssistantText. If the connection closes before a response arrives, the iterator rejects via rejectPendingLLM.
Throws
AbortError if the supplied _options.signal is aborted before the server responds.
Inherited from
BaseAgentProvider.generateFromMessages
getConfig()
getConfig(): BaseProviderConfig;
Defined in: src/providers/base/BaseProvider.ts:187
Get a shallow copy of the current provider configuration.
Returns
A new object containing all current configuration values.
Inherited from
initialize()
initialize(): Promise<void>;
Defined in: src/providers/base/BaseProvider.ts:127
Initialize the provider, making it ready for use.
Returns
Promise<void>
Remarks
Calls the subclass hook onInitialize. If the provider has already been initialized the call is a no-op.
Throws
ProviderInitializationError Thrown when onInitialize rejects. The original error is wrapped with the provider class name for diagnostics.
Inherited from
isAudioReady()
isAudioReady(chunk): boolean;
Defined in: src/providers/base/BaseAgentProvider.ts:458
Check whether an audio chunk is ready for playback.
Parameters
| Parameter | Type | Description |
|---|---|---|
chunk | AudioChunk | The audio chunk to inspect. |
Returns
boolean
true when the chunk contains a non-empty audio buffer.
Inherited from
BaseAgentProvider.isAudioReady
isFinal()
isFinal(result): boolean;
Defined in: src/providers/base/BaseAgentProvider.ts:294
Check whether a transcription is a final result.
Parameters
| Parameter | Type | Description |
|---|---|---|
result | TranscriptionResult | The transcription result to inspect. |
Returns
boolean
true when the result has isFinal set.
Inherited from
isInterim()
isInterim(_result): boolean;
Defined in: src/providers/base/BaseAgentProvider.ts:284
Check whether a transcription is an interim (non-final) result.
Parameters
| Parameter | Type | Description |
|---|---|---|
_result | TranscriptionResult | The transcription result to inspect. |
Returns
boolean
Always false for agent providers.
Remarks
Agent providers only surface final transcriptions — always returns false.
Inherited from
isPreflight()
isPreflight(_result): boolean;
Defined in: src/providers/base/BaseAgentProvider.ts:271
Check whether a transcription is a speculative preflight result.
Parameters
| Parameter | Type | Description |
|---|---|---|
_result | TranscriptionResult | The transcription result to inspect. |
Returns
boolean
Always false for agent providers.
Remarks
Agent providers do not emit preflight results — always returns false.
Inherited from
isReady()
isReady(): boolean;
Defined in: src/providers/base/BaseProvider.ts:178
Check whether the provider has been initialized and is ready.
Returns
boolean
true when initialize has completed successfully and dispose has not yet been called.
Inherited from
isUtteranceComplete()
isUtteranceComplete(result): boolean;
Defined in: src/providers/base/BaseAgentProvider.ts:258
Check whether a transcription marks the end of an utterance.
Parameters
| Parameter | Type | Description |
|---|---|---|
result | TranscriptionResult | The transcription result to inspect. |
Returns
boolean
true when the result has utteranceComplete set.
Inherited from
BaseAgentProvider.isUtteranceComplete
isWebSocketConnected()
isWebSocketConnected(): boolean;
Defined in: src/providers/agent/elevenlabs/ElevenLabsAgent.ts:345
Check whether the underlying WebSocket is currently open.
Returns
boolean
true if the WebSocket exists and its readyState is OPEN.
markAudioDone()
protected markAudioDone(): void;
Defined in: src/providers/base/BaseAgentProvider.ts:558
Signal that all audio for the current turn has been sent. Resolves the pending finalize() call.
Returns
void
Inherited from
BaseAgentProvider.markAudioDone
onAgentEvent()
onAgentEvent(callback): void;
Defined in: src/providers/agent/elevenlabs/ElevenLabsAgent.ts:298
Register a callback for ElevenLabs agent events.
Parameters
| Parameter | Type | Description |
|---|---|---|
callback | (event) => void | Invoked synchronously per event. Only one callback is active at a time; calling this again replaces the previous one. |
Returns
void
See
ElevenLabsAgentEvent for the event union
onAudio()
onAudio(callback): void;
Defined in: src/providers/base/BaseAgentProvider.ts:438
Register the audio callback.
Parameters
| Parameter | Type | Description |
|---|---|---|
callback | (chunk) => void | Invoked with an AudioChunk each time the agent sends a binary audio frame. |
Returns
void
Inherited from
onConfigUpdate()
protected onConfigUpdate(_config): void;
Defined in: src/providers/base/BaseProvider.ts:242
Hook called after updateConfig merges new values.
Parameters
| Parameter | Type | Description |
|---|---|---|
_config | Partial<BaseProviderConfig> | The partial configuration that was merged. |
Returns
void
Remarks
The default implementation is a no-op. Override in subclasses to react to runtime configuration changes (e.g. reconnect with a new API key).
Inherited from
BaseAgentProvider.onConfigUpdate
onDispose()
protected onDispose(): Promise<void>;
Defined in: src/providers/agent/elevenlabs/ElevenLabsAgent.ts:131
Provider-specific disposal logic.
Returns
Promise<void>
Remarks
Subclasses must implement this method to release any resources acquired during onInitialize (e.g. close connections, free memory).
Overrides
onInitialize()
protected onInitialize(): Promise<void>;
Defined in: src/providers/agent/elevenlabs/ElevenLabsAgent.ts:123
Provider-specific initialization logic.
Returns
Promise<void>
Remarks
Subclasses must implement this method to perform any setup required before the provider can be used (e.g. validate credentials, open connections, load models).
Overrides
BaseAgentProvider.onInitialize
onMetadata()
onMetadata(callback): void;
Defined in: src/providers/base/BaseAgentProvider.ts:448
Register the metadata callback.
Parameters
| Parameter | Type | Description |
|---|---|---|
callback | (metadata) => void | Invoked with an AudioMetadata object describing the audio format (sample rate, encoding, etc.). |
Returns
void
Inherited from
onTranscription()
onTranscription(callback): void;
Defined in: src/providers/base/BaseAgentProvider.ts:203
Register the transcription callback.
Parameters
| Parameter | Type | Description |
|---|---|---|
callback | (result) => void | Invoked with a TranscriptionResult each time the agent emits a user transcription event. |
Returns
void
Inherited from
BaseAgentProvider.onTranscription
processAudio()
processAudio(chunk): void;
Defined in: src/providers/base/BaseAgentProvider.ts:193
Forward microphone audio to the agent connection.
Parameters
| Parameter | Type | Description |
|---|---|---|
chunk | ArrayBuffer | Raw PCM audio data from the microphone input. |
Returns
void
Remarks
Alias for sendAudio — called by the orchestrator’s input queue.
See
Inherited from
BaseAgentProvider.processAudio
processChunk()
processChunk(_text): void;
Defined in: src/providers/base/BaseAgentProvider.ts:411
No-op alias for sendText.
Parameters
| Parameter | Type | Description |
|---|---|---|
_text | string | Text chunk (ignored by agent providers). |
Returns
void
Inherited from
BaseAgentProvider.processChunk
rejectPendingLLM()
protected rejectPendingLLM(error): void;
Defined in: src/providers/base/BaseAgentProvider.ts:571
Reject the pending LLM generator with an error.
Parameters
| Parameter | Type | Description |
|---|---|---|
error | Error | The error to propagate to the pending generateFromMessages iterator. |
Returns
void
Inherited from
BaseAgentProvider.rejectPendingLLM
resolveApiKey()
protected resolveApiKey(): Promise<string>;
Defined in: src/providers/base/BaseProvider.ts:321
Resolve the API key, calling the factory if apiKey is a function.
Returns
Promise<string>
The resolved API key string, or 'proxy' in proxy mode.
Inherited from
BaseAgentProvider.resolveApiKey
resolveAuthHeader()
protected resolveAuthHeader(defaultAuthType?): Promise<string | undefined>;
Defined in: src/providers/base/BaseProvider.ts:366
Resolve Authorization header value for the configured auth type.
Parameters
| Parameter | Type | Default value | Description |
|---|---|---|---|
defaultAuthType | "token" | "bearer" | 'token' | The default auth type for this provider. |
Returns
Promise<string | undefined>
The Authorization header value, or undefined in proxy mode.
Remarks
If apiKey is a factory function it is called to get a fresh token. Returns the header value for REST or server-side WebSocket connections:
'token'→'Token <apiKey>''bearer'→'Bearer <apiKey>'
Returns undefined in proxy mode.
Inherited from
BaseAgentProvider.resolveAuthHeader
resolveBaseUrl()
protected resolveBaseUrl(defaultUrl?): string | undefined;
Defined in: src/providers/base/BaseProvider.ts:307
Resolve the base URL for this provider.
Parameters
| Parameter | Type | Description |
|---|---|---|
defaultUrl? | string | The provider’s default API URL. Pass undefined to let the underlying SDK use its own default. |
Returns
string | undefined
The resolved URL, or undefined when all sources are unset.
Remarks
Priority: proxyUrl > endpoint > defaultUrl.
For WebSocket providers (this.type === 'websocket'), the proxy URL’s http(s) scheme is automatically converted to ws(s).
When no URL is configured and defaultUrl is undefined, the return value is undefined — this lets SDK-based providers (Anthropic, OpenAI) fall back to their own built-in defaults.
Inherited from
BaseAgentProvider.resolveBaseUrl
resolveWsProtocols()
protected resolveWsProtocols(defaultAuthType?): Promise<string[] | undefined>;
Defined in: src/providers/base/BaseProvider.ts:342
Resolve WebSocket subprotocol for authentication.
Parameters
| Parameter | Type | Default value | Description |
|---|---|---|---|
defaultAuthType | "token" | "bearer" | 'token' | The default auth type for this provider. |
Returns
Promise<string[] | undefined>
Subprotocol array for new WebSocket(url, protocols), or undefined.
Remarks
If apiKey is a factory function it is called to get a fresh token. Returns the subprotocol array for direct mode based on authType:
'token'→['token', apiKey](Deepgram default)'bearer'→['bearer', apiKey](OAuth/Bearer tokens)
Returns undefined in proxy mode (no client-side auth needed).
Inherited from
BaseAgentProvider.resolveWsProtocols
sendAudio()
sendAudio(chunk): void;
Defined in: src/providers/agent/elevenlabs/ElevenLabsAgent.ts:258
Send a raw audio chunk to the agent for speech recognition.
Parameters
| Parameter | Type | Description |
|---|---|---|
chunk | ArrayBuffer | Raw PCM16 audio at 16 kHz mono (the ConvAI default input format). The buffer is base64-encoded into a user_audio_chunk frame. |
Returns
void
Remarks
No-op when the WebSocket is not open — audio sent before connect completes or after the socket closes is silently dropped.
Overrides
sendContextualUpdate()
sendContextualUpdate(text): void;
Defined in: src/providers/agent/elevenlabs/ElevenLabsAgent.ts:325
Send background context to the agent without triggering a response.
Parameters
| Parameter | Type | Description |
|---|---|---|
text | string | Contextual information (e.g. “the user navigated to the pricing page”). |
Returns
void
Remarks
Sends a contextual_update frame. The agent factors the context into subsequent responses but does not reply to it directly.
sendText()
sendText(_chunk): void;
Defined in: src/providers/base/BaseAgentProvider.ts:404
No-op — TTS synthesis is handled server-side.
Parameters
| Parameter | Type | Description |
|---|---|---|
_chunk | string | Text chunk (ignored by agent providers). |
Returns
void
Inherited from
sendUserActivity()
sendUserActivity(): void;
Defined in: src/providers/agent/elevenlabs/ElevenLabsAgent.ts:336
Signal user activity to reset the agent’s inactivity timeout.
Returns
void
Remarks
Sends a user_activity frame. Useful to keep the conversation alive while the user is interacting silently (typing, reading).
sendUserMessage()
sendUserMessage(text): void;
Defined in: src/providers/agent/elevenlabs/ElevenLabsAgent.ts:311
Inject a text message as if the user typed it.
Parameters
| Parameter | Type | Description |
|---|---|---|
text | string | The user message content. |
Returns
void
Remarks
Sends a user_message frame. The agent responds exactly as it would to transcribed speech.
startKeepAlive()
protected startKeepAlive(intervalMs?, sendFn): void;
Defined in: src/providers/base/BaseAgentProvider.ts:594
Start an auto keep-alive timer. Call from your handshake completion.
Parameters
| Parameter | Type | Default value | Description |
|---|---|---|---|
intervalMs | number | 8_000 | Interval in milliseconds between keep-alive pings. Defaults to 8000 (8 seconds). |
sendFn | () => void | undefined | Callback invoked on each tick to send the provider-specific keep-alive message. |
Returns
void
Example
this.startKeepAlive(8_000, () => {
this.ws.send(JSON.stringify({ type: 'KeepAlive' }));
});
Inherited from
BaseAgentProvider.startKeepAlive
stopKeepAlive()
protected stopKeepAlive(): void;
Defined in: src/providers/base/BaseAgentProvider.ts:600
Stop the keep-alive timer.
Returns
void
Inherited from
BaseAgentProvider.stopKeepAlive
updateConfig()
updateConfig(config): void;
Defined in: src/providers/base/BaseProvider.ts:201
Merge partial configuration updates into the current config.
Parameters
| Parameter | Type | Description |
|---|---|---|
config | Partial<BaseProviderConfig> | A partial configuration object whose keys will overwrite existing values. |
Returns
void
Remarks
After merging, the subclass hook onConfigUpdate is called so providers can react to changed values at runtime.