Text-to-Speech

import os
from openai import AsyncOpenAI
from pydantic import Field
from timbal import Agent
from timbal.state import get_run_context
from timbal.types.file import File

async def tts(
    text: str = Field(
        ...,
        description="The text to convert to speech.",
    ),
) -> File:
    client = AsyncOpenAI(api_key=os.getenv("OPENAI_API_KEY"))
    
    kwargs = {
        "input": text,
        'model': 'tts-1',
        'voice': 'alloy'
    }
    
    response = await client.audio.speech.create(**kwargs)
    
    return File.validate(
        response.content,
        {"extension": ".mp3"}
    )

async def post_hook():
    """Post hook to extract and return the audio file."""
    span = get_run_context().current_span()
    span.output = await tts(text=span.output.content[0].text)
    span.output.to_disk("audio.mp3")

agent = Agent(
    name="VoiceAgent",
    model="openai/gpt-4.1-mini",
    post_hook=post_hook
)

# Agent will generate audio files
await agent(
    prompt="What is the capital of France?"
).collect()