audio.py

import os
from typing import IO
from io import BytesIO
from elevenlabs import VoiceSettings
from elevenlabs.client import ElevenLabs

ELEVENLABS_API_KEY = os.getenv("sk_030849f5720ff120d1e51afd8360dee0aca8622617e8c6a2")
client = ElevenLabs(
    api_key=ELEVENLABS_API_KEY,
)


def text_to_speech_stream(text: str) -> IO[bytes]:
    # Perform the text-to-speech conversion
    response = client.text_to_speech.convert(
        voice_id="pNInz6obpgDQGcFmaJgB", #pre-made voice
        optimize_streaming_latency="0",
        output_format="mp3_22050_32",
        text=text,
        model_id="eleven_multilingual_v2",
        voice_settings=VoiceSettings(
            stability=0.0,
            similarity_boost=1.0,
            style=0.0,
            use_speaker_boost=True,
        ),
    )


    audio_stream = BytesIO()


    for chunk in response:
        if chunk:
            audio_stream.write(chunk)


    audio_stream.seek(0)


    return audio_stream