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

Parameters

Union[str, BinaryIO]

required

Path to audio file or file-like object

Optional[str]

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

Optional[float]

Sampling temperature (0.0 to 1.0)

Optional[str]

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

Returns

str

Transcribed text

Usage

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

Uses

transcription
close

Used By

AudioAgent.listen

Source

View on GitHub

praisonaiagents/agent/audio_agent.py at line 313

Guide

Reference

transcribe • AI Agent SDK

transcribe

Signature

Parameters

Returns

Usage

Uses

Used By

Source

View on GitHub

​transcribe

​Signature

​Parameters

​Returns

​Usage

​Uses

​Used By

​Source

View on GitHub

transcribe

Signature

Parameters

Returns

Usage

Uses

Used By

Source