TTS

pipecat.services.neuphonic.tts.language_to_neuphonic_lang_code(language)

Parameters:

language (Language)

Return type:

str | None

class pipecat.services.neuphonic.tts.NeuphonicTTSService(*, api_key, voice_id=None, url='wss://api.neuphonic.com', sample_rate=22050, encoding='pcm_linear', params=None, **kwargs)

Bases: InterruptibleTTSService

Parameters:

• api_key (str)

• voice_id (str | None)

• url (str)

• sample_rate (int | None)

• encoding (str)

• params (InputParams | None)

class InputParams(*, language=Language.EN, speed=1.0)

Bases: BaseModel

Parameters:

• language (Language | None)

• speed (float | None)

language: Language | None

speed: float | 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 start(frame)

Start the TTS service.

Parameters:

frame (StartFrame) – The start frame containing initialization parameters.

async stop(frame)

Stop the TTS service.

Parameters:

frame (EndFrame) – The end frame.

async cancel(frame)

Cancel the TTS service.

Parameters:

frame (CancelFrame) – The cancel frame.

async flush_audio()

Flush any buffered audio data.

async push_frame(frame, direction=FrameDirection.DOWNSTREAM)

Push a frame downstream with TTS-specific handling.

Parameters:

• frame (Frame) – The frame to push.

• direction (FrameDirection) – The direction to push the frame.

async process_frame(frame, direction)

Process frames with bot speaking state tracking.

Parameters:

• frame (Frame) – The frame to process.

• direction (FrameDirection) – The direction of frame processing.

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.neuphonic.tts.NeuphonicHttpTTSService(*, api_key, voice_id=None, url='https://api.neuphonic.com', sample_rate=22050, encoding='pcm_linear', params=None, **kwargs)

Bases: TTSService

Neuphonic Text-to-Speech service using HTTP streaming.

Parameters:

• api_key (str) – Neuphonic API key

• voice_id (str | None) – ID of the voice to use

• url (str) – Base URL for the Neuphonic API (default: “https://api.neuphonic.com”)

• sample_rate (int | None) – Sample rate for audio output (default: 22050Hz)

• encoding (str) – Audio encoding format (default: “pcm_linear”)

• params (InputParams | None) – Additional parameters for TTS generation including language and speed

• **kwargs – Additional keyword arguments passed to the parent class

class InputParams(*, language=Language.EN, speed=1.0)

Bases: BaseModel

Parameters:

• language (Language | None)

• speed (float | None)

language: Language | None

speed: float | 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

async start(frame)

Start the TTS service.

Parameters:

frame (StartFrame) – The start frame containing initialization parameters.

async flush_audio()

Flush any buffered audio data.

async run_tts(text)

Generate speech from text using Neuphonic streaming API.

Parameters:

text (str) – The text to convert to speech

Yields:

Frames containing audio data and status information

Return type:

AsyncGenerator[Frame, None]