TTS

pipecat.services.google.tts.language_to_google_tts_language(language)

Parameters:

language (Language)

Return type:

str | None

class pipecat.services.google.tts.GoogleHttpTTSService(*, credentials=None, credentials_path=None, voice_id='en-US-Chirp3-HD-Charon', sample_rate=None, params=None, **kwargs)

Bases: TTSService

Parameters:

• credentials (str | None)

• credentials_path (str | None)

• voice_id (str)

• sample_rate (int | None)

• params (InputParams | None)

class InputParams(*, pitch=None, rate=None, volume=None, emphasis=None, language=Language.EN, gender=None, google_style=None)

Bases: BaseModel

Parameters:

• pitch (str | None)

• rate (str | None)

• volume (str | None)

• emphasis (Literal['strong', 'moderate', 'reduced', 'none'] | None)

• language (Language | None)

• gender (Literal['male', 'female', 'neutral'] | None)

• google_style (Literal['apologetic', 'calm', 'empathetic', 'firm', 'lively'] | None)

pitch: str | None

rate: str | None

volume: str | None

emphasis: Literal['strong', 'moderate', 'reduced', 'none'] | None

language: Language | None

gender: Literal['male', 'female', 'neutral'] | None

google_style: Literal['apologetic', 'calm', 'empathetic', 'firm', 'lively'] | None

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

can_generate_metrics()

Return type:

bool

language_to_service_language(language)

Convert a language to the service-specific language format.

Parameters:

language (Language) – The language to convert.

Returns:

The service-specific language identifier, or None if not supported.

Return type:

str | None

async run_tts(text)

Run text-to-speech synthesis on the provided text.

This method must be implemented by subclasses to provide actual TTS functionality.

Parameters:

text (str) – The text to synthesize into speech.

Yields:

Frame – Audio frames containing the synthesized speech.

Return type:

AsyncGenerator[Frame, None]

class pipecat.services.google.tts.GoogleTTSService(*, credentials=None, credentials_path=None, voice_id='en-US-Chirp3-HD-Charon', sample_rate=None, params=InputParams(language=<Language.EN: 'en'>), **kwargs)

Bases: TTSService

Text-to-Speech service using Google Cloud Text-to-Speech API.

Converts text to speech using Google’s TTS models with streaming synthesis for low latency. Supports multiple languages and voices.

Parameters:

• credentials (str | None) – JSON string containing Google Cloud service account credentials.

• credentials_path (str | None) – Path to Google Cloud service account JSON file.

• voice_id (str) – Google TTS voice identifier (e.g., “en-US-Chirp3-HD-Charon”).

• sample_rate (int | None) – Audio sample rate in Hz.

• params (InputParams) – Language only.

Notes

Requires Google Cloud credentials via service account JSON, file path, or default application credentials (GOOGLE_APPLICATION_CREDENTIALS env var). Only Chirp 3 HD and Journey voices are supported. Use GoogleHttpTTSService for other voices.

Example

```python tts = GoogleTTSService(

credentials_path=”/path/to/service-account.json”, voice_id=”en-US-Chirp3-HD-Charon”, params=GoogleTTSService.InputParams(

language=Language.EN_US,

)

)

class InputParams(*, language=Language.EN)

Bases: BaseModel

Parameters:

language (Language | None)

language: Language | None

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

can_generate_metrics()

Return type:

bool

language_to_service_language(language)

Convert a language to the service-specific language format.

Parameters:

language (Language) – The language to convert.

Returns:

The service-specific language identifier, or None if not supported.

Return type:

str | None

async run_tts(text)

Run text-to-speech synthesis on the provided text.

This method must be implemented by subclasses to provide actual TTS functionality.

Parameters:

text (str) – The text to synthesize into speech.

Yields:

Frame – Audio frames containing the synthesized speech.

Return type:

AsyncGenerator[Frame, None]