Google

GoogleTTS

Google Cloud text-to-speech (TTS) provider. The model family must be consistent with voice; mismatches throw, and an unknown family is passed through (routing falls back to the voice name).

Constructor

new GoogleTTS(opts: GoogleTTSOptions)

apiKey

string | null

Google API key. Falls back to the GOOGLE_API_KEY environment variable, then null.

credentialsJson

string | null

Service-account credentials as a JSON string. Default null.

serviceAccountPath

string | null

Path to a service-account JSON key file. Default null.

stream

boolean

Stream audio from the model. Default true.

voice

string

Voice name to synthesize with (e.g. 'en-US-Neural2-F'). Default 'en-US-Neural2-F'.

languageCode

string

BCP-47 language code. Default 'en-US'.

model

GoogleTTSModel | string

Voice model family (e.g. 'neural2', 'wavenet', 'chirp3-hd'). Must match the voice’s family; omit (default '') to let the voice decide. Known families: standard, wavenet, neural2, news, polyglot, studio, chirp, chirp-hd, chirp3-hd.

sampleRate

number

Output audio sample rate in Hz. Default 24000.

speakingRate

number | null

Speaking rate (1.0 = normal). Must be in [0.25, 4.0]. Default null (provider default).

pitch

number | null

Voice pitch in semitones (0 = normal). Must be in [-20.0, 20.0]. Default null (provider default).

voiceConfig

GoogleVoiceConfig | null

Voice selection used as a fallback for voice and languageCode when those are left at their defaults. Default null.

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>

interrupt

interrupt(): Promise<void>

Stop the current synthesis.

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

onFirstAudioByte

onFirstAudioByte(callback: FirstAudioByteCallback): void

callback

FirstAudioByteCallback

required

removeAllListeners

removeAllListeners(event?: string): void

event

string

synthesize

synthesize(text: any, ..._extra: any[]): Promise<void>

Synthesize and speak text on the active session.

text

any

required

GoogleTTSModel

Supported Google Cloud TTS voice model families.

type GoogleTTSModel = | 'chirp3-hd' | 'chirp-hd' | 'studio' | 'neural2' | 'wavenet' | 'standard' | 'news' | 'polyglot' | 'chirp'

Node JS SDK

Core

Speech-to-text

LLM

Text-to-speech

Realtime models

Avatars

Turn detection

Voice activity detection

Noise cancellation

GoogleTTS

Constructor

close

closeEmitter

emit

getRuntimeConfig

interrupt

listenerCount

off

on

once

onFirstAudioByte

removeAllListeners

synthesize

GoogleTTSModel

​GoogleTTS

​Constructor

​close

​closeEmitter

​emit

​getRuntimeConfig

​interrupt

​listenerCount

​off

​on

​once

​onFirstAudioByte

​removeAllListeners

​synthesize

​GoogleTTSModel

GoogleTTS

Constructor

close

closeEmitter

emit

getRuntimeConfig

interrupt

listenerCount

off

on

once

onFirstAudioByte

removeAllListeners

synthesize

GoogleTTSModel