STT

class pipecat.services.sambanova.stt.SambaNovaSTTService(*, model='Whisper-Large-v3', api_key=None, base_url='https://api.sambanova.ai/v1', language=Language.EN, prompt=None, temperature=None, **kwargs)[source]

Bases: BaseWhisperSTTService

SambaNova Whisper speech-to-text service. Uses SambaNova’s Whisper API to convert audio to text. Requires a SambaNova API key set via the api_key parameter or SAMBANOVA_API_KEY environment variable. :param model: Whisper model to use. Defaults to “Whisper-Large-v3”. :param api_key: SambaNova API key. Defaults to None. :param base_url: API base URL. Defaults to “https://api.sambanova.ai/v1”. :param language: Language of the audio input. Defaults to English. :param prompt: Optional text to guide the model’s style or continue a previous segment. :param temperature: Optional sampling temperature between 0 and 1. Defaults to 0.0. :param **kwargs: Additional arguments passed to pipecat.services.whisper.base_stt.BaseWhisperSTTService.

Parameters:

  • model (str)

  • api_key (str | None)

  • base_url (str)

  • language (Language | None)

  • prompt (str | None)

  • temperature (float | None)

  • kwargs (Any)