transcribe

Method

This is a method of the AudioAgent class in the audio_agent module.

Transcribe audio to text.

Signature

def transcribe(file: Union[str, BinaryIO], language: Optional[str], temperature: Optional[float], model: Optional[str]) -> str

file

Union

required

Path to audio file or file-like object

language

Optional

Language code (e.g., “en”, “es”, “fr”)

temperature

Optional

Sampling temperature (0.0 to 1.0)

model

Optional

Override model for this call **kwargs: Additional provider-specific parameters

str

Transcribed text

agent = AudioAgent(llm="openai/whisper-1")
    text = agent.transcribe("audio.mp3")
    print(text)