Skip to main content

​
speech

Method
This is a method of the AudioAgent class in the audio_agent module.
Convert text to speech.

​
Signature

def speech(text: str, output: Optional[str], voice: Optional[str], speed: Optional[float], response_format: Optional[str], model: Optional[str]) -> Any

​
Parameters

​
text
str
required
Text to convert to speech
​
output
Optional
Path to save audio file (optional)
​
voice
Optional
Voice to use (e.g., “alloy”, “echo”, “fable”)
​
speed
Optional
Speech speed (0.25 to 4.0)
​
response_format
Optional
Audio format (mp3, opus, aac, flac, wav)
​
model
Optional
Override model for this call **kwargs: Additional provider-specific parameters

​
Returns

​
Returns
Any
Audio response object with stream_to_file() method

​
Usage

agent = AudioAgent(llm="openai/tts-1")
    agent.speech("Hello world!", output="hello.mp3")