TTS

class pipecat.services.riva.tts.RivaTTSService(*, api_key, server='grpc.nvcf.nvidia.com:443', voice_id='Magpie-Multilingual.EN-US.Ray', sample_rate=None, model_function_map={'function_id': '877104f7-e885-42b9-8de8-f6e4c6303969', 'model_name': 'magpie-tts-multilingual'}, params=None, **kwargs)

Bases: TTSService

Parameters:

• api_key (str)

• server (str)

• voice_id (str)

• sample_rate (int | None)

• model_function_map (Mapping[str, str])

• params (InputParams | None)

class InputParams(*, language=Language.EN_US, quality=20)

Bases: BaseModel

Parameters:

• language (Language | None)

• quality (int | None)

language: Language | None

quality: int | None

model_config: ClassVar[ConfigDict] = {}

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

async set_model(model)

Set the TTS model to use.

Parameters:

model (str) – The name of the TTS model.

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.riva.tts.FastPitchTTSService(*, api_key, server='grpc.nvcf.nvidia.com:443', voice_id='English-US.Female-1', sample_rate=None, model_function_map={'function_id': '0149dedb-2be8-4195-b9a0-e57e0e14f972', 'model_name': 'fastpitch-hifigan-tts'}, params=None, **kwargs)

Bases: RivaTTSService

Parameters:

• api_key (str)

• server (str)

• voice_id (str)

• sample_rate (int | None)

• model_function_map (Mapping[str, str])

• params (InputParams | None)