NativeSTT

Defined in: src/providers/stt/native/NativeSTT.ts:168

Native browser STT provider backed by the Web Speech API (SpeechRecognition).

Remarks

Unlike other STT providers, NativeSTT manages its own audio pipeline — the browser’s SpeechRecognition API directly accesses the microphone. Because of this, the provider declares roles: ['input', 'stt'] and CompositeVoice will not set up a separate AudioInputProvider. The sendAudioToSocket method is a no-op.

Transport: WebSocket-like (browser-managed, extends LiveSTTProvider)

Browser support:

• Chrome / Edge (Chromium): Full support via SpeechRecognition
• Safari: Partial support via webkitSpeechRecognition
• Firefox: Not supported (as of 2025)

Data flow:

Microphone -> SpeechRecognition API (browser) -> onresult event
                                                     |
CompositeVoice <- onTranscription(result) <---------+

Example

import { NativeSTT } from 'composite-voice';

const stt = new NativeSTT({
  language: 'en-US',
  continuous: true,
  interimResults: true,
  maxAlternatives: 1,
});

await stt.initialize();

stt.onTranscription((result) => {
  console.log(result.text, result.isFinal);
});

await stt.connect(); // starts listening
// ... later ...
await stt.disconnect(); // stops listening

See

• LiveSTTProvider for the base WebSocket STT class
• NativeSTTConfig for configuration options
• DeepgramSTT for an alternative real-time STT provider

Extends

• LiveSTTProvider

Constructors

Constructor

new NativeSTT(config?, logger?): NativeSTT;

Defined in: src/providers/stt/native/NativeSTT.ts:203

Create a new NativeSTT provider.

Parameters

Returns

NativeSTT

Example

const stt = new NativeSTT({ language: 'fr-FR', continuous: false });

Overrides

LiveSTTProvider.constructor

Properties

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

LiveSTTProvider.isProxyMode

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

LiveSTTProvider.assertAuth

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

LiveSTTProvider.assertReady

connect()

connect(): Promise<void>;

Defined in: src/providers/stt/native/NativeSTT.ts:410

Start the browser’s speech recognition engine.

Returns

Promise<void>

Remarks

Checks microphone permission, then calls SpeechRecognition.start(). The returned promise resolves once the browser fires the onstart event, or rejects if the start times out or permission is denied.

Throws

ProviderConnectionError Thrown when the provider is not initialized, microphone permission is denied, or the recognition engine does not start within startTimeout milliseconds.

Overrides

LiveSTTProvider.connect

disconnect()

disconnect(): Promise<void>;

Defined in: src/providers/stt/native/NativeSTT.ts:492

Stop the browser’s speech recognition engine.

Returns

Promise<void>

Resolves immediately after requesting the stop.

Remarks

Calls SpeechRecognition.stop(). If the recognition instance has already been stopped, the error is silently ignored.

Overrides

LiveSTTProvider.disconnect

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

LiveSTTProvider.dispose

emitTranscription()

protected emitTranscription(result): void;

Defined in: src/providers/base/BaseSTTProvider.ts:206

Emit a transcription result to the registered callback.

Parameters

Returns

void

Remarks

Subclasses call this method whenever transcribed text is available. If no callback has been registered via onTranscription, the result is logged as a warning and dropped.

Inherited from

LiveSTTProvider.emitTranscription

getConfig()

getConfig(): STTProviderConfig;

Defined in: src/providers/base/BaseSTTProvider.ts:225

Get a shallow copy of the current STT configuration.

Returns

STTProviderConfig

A new STTProviderConfig object.

Inherited from

LiveSTTProvider.getConfig

getMetadata()

getMetadata(): AudioMetadata;

Defined in: src/providers/stt/native/NativeSTT.ts:639

Returns sensible audio metadata defaults for the Web Speech API.

Returns

AudioMetadata

AudioMetadata with sampleRate: 16000, encoding: 'linear16', channels: 1, bitDepth: 16

Remarks

The Web Speech API does not expose the actual audio format it uses internally, so this returns reasonable defaults matching the most common browser configuration. These values are used by the pipeline’s STT metadata auto-configuration when NativeSTT is the input provider.

See

AudioInputProvider.getMetadata

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

LiveSTTProvider.initialize

isActive()

isActive(): boolean;

Defined in: src/providers/stt/native/NativeSTT.ts:605

Check whether the SpeechRecognition engine is actively listening.

Returns

boolean

true when recognition is active (between connect() and disconnect()).

See

AudioInputProvider.isActive

isConnected()

isConnected(): boolean;

Defined in: src/providers/stt/native/NativeSTT.ts:516

Check whether the SpeechRecognition instance exists and is ready.

Returns

boolean

true when the recognition object has been created (after initialization).

isFinal()

isFinal(result): boolean;

Defined in: src/providers/base/BaseSTTProvider.ts:174

Is this a final segment (but not necessarily utterance-complete)?

Parameters

Returns

boolean

true when this is a final segment.

Remarks

A final segment represents committed text, but multi-segment providers (e.g., Deepgram) may emit several final segments for a single utterance. Only the last one will have isUtteranceComplete return true.

Inherited from

LiveSTTProvider.isFinal

isInterim()

isInterim(result): boolean;

Defined in: src/providers/base/BaseSTTProvider.ts:159

Is this an interim (partial, non-final) result?

Parameters

Returns

boolean

true when this is an interim result.

Remarks

Interim results update as the user speaks and are replaced by subsequent results. Useful for display but not for triggering downstream processing.

Inherited from

LiveSTTProvider.isInterim

isPreflight()

isPreflight(result): boolean;

Defined in: src/providers/base/BaseSTTProvider.ts:144

Is this a preflight/eager end-of-turn signal?

Parameters

Returns

boolean

true when this is a preflight signal.

Remarks

Used by the eager LLM pipeline for speculative generation. Only providers with preflight support (e.g., Deepgram Flux) need to override this.

Inherited from

LiveSTTProvider.isPreflight

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

LiveSTTProvider.isReady

isUtteranceComplete()

isUtteranceComplete(result): boolean;

Defined in: src/providers/base/BaseSTTProvider.ts:129

Is this result a complete utterance ready for LLM processing?

Parameters

Returns

boolean

true when the utterance is complete.

Remarks

The orchestrator calls this to decide when to send transcribed text to the LLM. Concrete providers override this when they have domain- specific endpointing logic (e.g., DeepgramSTT checks speech_final).

Inherited from

LiveSTTProvider.isUtteranceComplete

onAudio()

onAudio(_callback): void;

Defined in: src/providers/stt/native/NativeSTT.ts:621

No-op — NativeSTT directly accesses the microphone via the browser’s SpeechRecognition API and does not emit raw audio chunks.

Parameters

Returns

void

Remarks

The browser handles audio capture internally. This method exists solely to satisfy the AudioInputProvider interface.

See

AudioInputProvider.onAudio

onConfigUpdate()

protected onConfigUpdate(_config): void;

Defined in: src/providers/base/BaseProvider.ts:242

Hook called after updateConfig merges new values.

Parameters

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

LiveSTTProvider.onConfigUpdate

onDispose()

protected onDispose(): Promise<void>;

Defined in: src/providers/stt/native/NativeSTT.ts:260

Disconnect and release the SpeechRecognition instance.

Returns

Promise<void>

Overrides

LiveSTTProvider.onDispose

onInitialize()

protected onInitialize(): Promise<void>;

Defined in: src/providers/stt/native/NativeSTT.ts:220

Initialize the SpeechRecognition instance and configure it.

Returns

Promise<void>

Throws

Error Thrown when the Web Speech API is not available in the current browser.

Overrides

LiveSTTProvider.onInitialize

onTranscription()

onTranscription(callback): void;

Defined in: src/providers/base/BaseSTTProvider.ts:191

Register a callback to receive transcription results.

Parameters

Returns

void

Remarks

All STT providers — regardless of transport — deliver text through this callback. CompositeVoice registers it during pipeline setup so that transcription results flow into the conversation manager and, ultimately, the LLM provider.

Inherited from

LiveSTTProvider.onTranscription

pause()

pause(): void;

Defined in: src/providers/stt/native/NativeSTT.ts:580

Pause audio capture by stopping recognition.

Returns

void

Remarks

The Web Speech API’s SpeechRecognition does not support a native pause operation, so this delegates to disconnect() to halt recognition. Use resume() to restart.

See

AudioInputProvider.pause

processAudio()

processAudio(chunk): void;

Defined in: src/providers/base/LiveSTTProvider.ts:140

Process a raw audio chunk by sending it over the WebSocket.

Parameters

Returns

void

Remarks

Legacy alias for sendAudio. Delegates to sendAudioToSocket.

Inherited from

LiveSTTProvider.processAudio

resolveApiKey()

protected resolveApiKey(): string;

Defined in: src/providers/base/BaseProvider.ts:325

Resolve the API key for this provider.

Returns

string

The configured API key, or 'proxy' in proxy mode.

Remarks

Returns 'proxy' in proxy mode so that SDK clients (which require a non-empty API key string) can be instantiated without the real key.

Inherited from

LiveSTTProvider.resolveApiKey

resolveAuthHeader()

protected resolveAuthHeader(defaultAuthType?): string | undefined;

Defined in: src/providers/base/BaseProvider.ts:366

Resolve Authorization header value for the configured auth type.

Parameters

Returns

string | undefined

The Authorization header value, or undefined in proxy mode.

Remarks

Returns the header value for REST or server-side WebSocket connections:

• 'token' → 'Token <apiKey>'
• 'bearer' → 'Bearer <apiKey>'

Returns undefined in proxy mode.

Inherited from

LiveSTTProvider.resolveAuthHeader

resolveBaseUrl()

protected resolveBaseUrl(defaultUrl?): string | undefined;

Defined in: src/providers/base/BaseProvider.ts:307

Resolve the base URL for this provider.

Parameters

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

LiveSTTProvider.resolveBaseUrl

resolveWsProtocols()

protected resolveWsProtocols(defaultAuthType?): string[] | undefined;

Defined in: src/providers/base/BaseProvider.ts:343

Resolve WebSocket subprotocol for authentication.

Parameters

Returns

string[] | undefined

Subprotocol array for new WebSocket(url, protocols), or undefined.

Remarks

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

LiveSTTProvider.resolveWsProtocols

resume()

resume(): void;

Defined in: src/providers/stt/native/NativeSTT.ts:593

Resume audio capture after a pause.

Returns

void

Remarks

Delegates to connect() to restart the SpeechRecognition engine after a pause().

See

AudioInputProvider.resume

sendAudio()

sendAudio(chunk): void;

Defined in: src/providers/base/LiveSTTProvider.ts:128

Send an audio chunk for real-time transcription.

Parameters

Returns

void

Remarks

This is the public method required by the ILiveSTTProvider interface. It delegates to sendAudioToSocket, which subclasses implement to forward audio data over the WebSocket connection. For providers that manage their own audio (e.g. NativeSTT), sendAudioToSocket is a no-op.

Inherited from

LiveSTTProvider.sendAudio

sendAudioToSocket()

protected sendAudioToSocket(_chunk): void;

Defined in: src/providers/stt/native/NativeSTT.ts:532

No-op — NativeSTT directly accesses the microphone via the SpeechRecognition API and does not accept external audio data.

Parameters

Returns

void

Remarks

CompositeVoice should not call this method because NativeSTT covers the 'input' role internally. Any invocation is silently ignored.

Called by the base class’s processAudio() method.

Overrides

LiveSTTProvider.sendAudioToSocket

start()

start(): void;

Defined in: src/providers/stt/native/NativeSTT.ts:553

Start capturing audio via the browser’s SpeechRecognition API.

Returns

void

Remarks

Delegates to connect(). This method exists to satisfy the AudioInputProvider interface for duck-type validation in the provider resolution algorithm. In the multi-role simplified path, the orchestrator calls connect() directly.

See

AudioInputProvider.start

stop()

stop(): void;

Defined in: src/providers/stt/native/NativeSTT.ts:565

Stop capturing audio via the browser’s SpeechRecognition API.

Returns

void

Remarks

Delegates to disconnect().

See

AudioInputProvider.stop

updateConfig()

updateConfig(config): void;

Defined in: src/providers/base/BaseProvider.ts:201

Merge partial configuration updates into the current config.

Parameters

Returns

void

Remarks

After merging, the subclass hook onConfigUpdate is called so providers can react to changed values at runtime.

Inherited from

LiveSTTProvider.updateConfig