Azure

AzureSTT

Azure (Cognitive Services) speech-to-text provider. Creates a configured Azure Speech STT provider for use in a voice agent.

Constructor

new AzureSTT(opts: AzureSTTOptions)

speechKey

string

Azure Speech key. Falls back to the AZURE_SPEECH_KEY env var.

speechRegion

string

Azure Speech region. Falls back to the AZURE_REGION env var, then 'eastus'.

language

string

Recognition language code. Default: 'en-US'.

sampleRate

number

Input audio sample rate in Hz. Default: 16000.

enablePhraseList

boolean

Enable a phrase list to bias recognition.

phraseList

string[]

Phrases to bias recognition toward.

close

close(): Promise<void>

Release any resources held by the provider.

closeEmitter

closeEmitter(): Promise<void>

Close the emitter: drop all handlers and stop emitting. Waits up to 2 seconds for in-flight async handlers to settle before returning.

emit

emit(event: string, ...args: any[]): void

event

string

required

getRuntimeConfig

getRuntimeConfig(): Record<string, any>

returns

Record<string, any>

listenerCount

listenerCount(event: string): number

event

string

required

returns

number

off

off(event: string, handler: EventHandler): void

event

string

required

handler

EventHandler

required

on

on(event: string, handler: EventHandler): EventHandler

event

string

required

handler

EventHandler

required

returns

EventHandler

once

once(event: string, handler: EventHandler): EventHandler

event

string

required

handler

EventHandler

required

returns

EventHandler

onSttTranscript

onSttTranscript(callback: SttTranscriptCallback): void

callback

SttTranscriptCallback

required

processAudio

processAudio(_audioFrames: Uint8Array, _language?: string | null, ..._extra: any[]): Promise<void>

Process a buffer of audio frames. Override in a custom provider.

removeAllListeners

removeAllListeners(event?: string): void

event

string

streamTranscribe

streamTranscribe(_audioStream: AsyncIterable<Uint8Array>, ..._extra: any[]): AsyncIterator<STTResponse>

Transcribe a streaming audio source, yielding STTResponses. Override in a custom provider.

returns

AsyncIterator<STTResponse>

AzureOpenAISTT

Azure OpenAI speech-to-text provider. Creates a configured Azure OpenAI transcription provider for use in a voice agent.

Constructor

new AzureOpenAISTT(opts: AzureOpenAISTTOptions)

apiKey

string | null

Azure OpenAI API key. Falls back to the AZURE_API_KEY then AZURE_OPENAI_API_KEY env vars, then null.

azureEndpoint

string | null

Azure OpenAI resource endpoint. Falls back to the AZURE_OPENAI_ENDPOINT env var, then null.

deployment

string | null

Azure deployment name. Falls back to the AZURE_OPENAI_STT_DEPLOYMENT env var, then null.

apiVersion

string

Azure OpenAI REST API version. Default: '2025-03-01-preview'.

model

AzureOpenAISTTModel | string

Transcription model name. Default: ''.

language

string

Transcription language code. Default: 'en'.

stream

boolean

Whether to use streaming transcription. Default: false.

inputSampleRate

number

Input audio sample rate in Hz. Default: 48000.

outputSampleRate

number

Output audio sample rate in Hz. Default: 24000.

prompt

string | null

Optional prompt to bias transcription. Default: null.

temperature

number | null

Sampling temperature. Default: null.

responseFormat

string

Response format, e.g. 'json', 'text'. Default: 'json'.

turnDetection

string

Turn-detection mode, e.g. 'server_vad'. Default: 'server_vad'.

close

close(): Promise<void>

Release any resources held by the provider.

closeEmitter

closeEmitter(): Promise<void>

Close the emitter: drop all handlers and stop emitting. Waits up to 2 seconds for in-flight async handlers to settle before returning.

emit

emit(event: string, ...args: any[]): void

event

string

required

getRuntimeConfig

getRuntimeConfig(): Record<string, any>

returns

Record<string, any>

listenerCount

listenerCount(event: string): number

event

string

required

returns

number

off

off(event: string, handler: EventHandler): void

event

string

required

handler

EventHandler

required

on

on(event: string, handler: EventHandler): EventHandler

event

string

required

handler

EventHandler

required

returns

EventHandler

once

once(event: string, handler: EventHandler): EventHandler

event

string

required

handler

EventHandler

required

returns

EventHandler

onSttTranscript

onSttTranscript(callback: SttTranscriptCallback): void

callback

SttTranscriptCallback

required

processAudio

processAudio(_audioFrames: Uint8Array, _language?: string | null, ..._extra: any[]): Promise<void>

Process a buffer of audio frames. Override in a custom provider.

removeAllListeners

removeAllListeners(event?: string): void

event

string

streamTranscribe

streamTranscribe(_audioStream: AsyncIterable<Uint8Array>, ..._extra: any[]): AsyncIterator<STTResponse>

Transcribe a streaming audio source, yielding STTResponses. Override in a custom provider.

returns

AsyncIterator<STTResponse>

AzureOpenAISTTModel

Supported Azure OpenAI STT transcription model names.

type AzureOpenAISTTModel = 'gpt-4o-transcribe' | 'gpt-4o-mini-transcribe' | 'gpt-4o-transcribe-diarize' | 'whisper'

Node JS SDK

Core

Speech-to-text

LLM

Text-to-speech

Realtime models

Avatars

Turn detection

Voice activity detection

Noise cancellation

AzureSTT

Constructor

close

closeEmitter

emit

getRuntimeConfig

listenerCount

off

on

once

onSttTranscript

processAudio

removeAllListeners

streamTranscribe

AzureOpenAISTT

Constructor

close

closeEmitter

emit

getRuntimeConfig

listenerCount

off

on

once

onSttTranscript

processAudio

removeAllListeners

streamTranscribe

AzureOpenAISTTModel

​AzureSTT

​Constructor

​close

​closeEmitter

​emit

​getRuntimeConfig

​listenerCount

​off

​on

​once

​onSttTranscript

​processAudio

​removeAllListeners

​streamTranscribe

​AzureOpenAISTT

​Constructor

​close

​closeEmitter

​emit

​getRuntimeConfig

​listenerCount

​off

​on

​once

​onSttTranscript

​processAudio

​removeAllListeners

​streamTranscribe

​AzureOpenAISTTModel

AzureSTT

Constructor

close

closeEmitter

emit

getRuntimeConfig

listenerCount

off

on

once

onSttTranscript

processAudio

removeAllListeners

streamTranscribe

AzureOpenAISTT

Constructor

close

closeEmitter

emit

getRuntimeConfig

listenerCount

off

on

once

onSttTranscript

processAudio

removeAllListeners

streamTranscribe

AzureOpenAISTTModel