STT

pipecat.services.gladia.stt.language_to_gladia_language(language)

Convert a Language enum to Gladia’s language code format.

Parameters:

language (Language) – The Language enum value to convert

Returns:

The Gladia language code string or None if not supported

Return type:

str | None

class pipecat.services.gladia.stt.GladiaSTTService(*, api_key, url='https://api.gladia.io/v2/live', confidence=0.5, sample_rate=None, model='solaria-1', params=None, max_reconnection_attempts=5, reconnection_delay=1.0, max_buffer_size=20971520, **kwargs)

Bases: STTService

Speech-to-Text service using Gladia’s API.

This service connects to Gladia’s WebSocket API for real-time transcription with support for multiple languages, custom vocabulary, and various processing options.

For complete API documentation, see: https://docs.gladia.io/api-reference/v2/live/init

Parameters:

• api_key (str)

• url (str)

• confidence (float)

• sample_rate (int | None)

• model (str)

• params (GladiaInputParams | None)

• max_reconnection_attempts (int)

• reconnection_delay (float)

• max_buffer_size (int)

InputParams

alias of GladiaInputParams

can_generate_metrics()

Return type:

bool

language_to_service_language(language)

Convert pipecat Language enum to Gladia’s language code.

Parameters:

language (Language)

Return type:

str | None

async start(frame)

Start the Gladia STT websocket connection.

Parameters:

frame (StartFrame)

async stop(frame)

Stop the Gladia STT websocket connection.

Parameters:

frame (EndFrame)

async cancel(frame)

Cancel the Gladia STT websocket connection.

Parameters:

frame (CancelFrame)

async run_stt(audio)

Run speech-to-text on audio data.

Parameters:

audio (bytes)

Return type:

AsyncGenerator[Frame, None]