services/tts_service.py

from services.gemini_client import get_gemini_client
from google.genai import types
import base64
import logging

logger = logging.getLogger(__name__)


async def generate_tts(text: str) -> bytes:
    """
    Convert text to speech using Gemini API.
    
    Args:
        text: Text to convert to speech
    
    Returns:
        Audio bytes in WAV format
    
    Raises:
        Exception: If TTS generation fails
    """
    try:
        client = get_gemini_client()
        
        logger.info(f"Generating speech for: '{text}'")
        
        # Call Gemini TTS API
        response = client.models.generate_content(
            model="gemini-2.5-flash-preview-tts",
            contents=text,
            config=types.GenerateContentConfig(
                response_modalities=["AUDIO"],
                speech_config=types.SpeechConfig(
                    voice_config=types.VoiceConfig(
                        prebuilt_voice_config=types.PrebuiltVoiceConfig(
                            voice_name="Kore"  # Options: Kore, Peri, Charon, Fenrir, Orbit
                        )
                    )
                ),
            ),
        )
        
        # Extract and decode base64 audio
        audio_base64 = response.candidates[0].content.parts[0].inline_data.data
        audio_bytes = base64.b64decode(audio_base64)
        
        logger.info(f"✓ TTS successful: {len(audio_bytes)} bytes generated")
        
        return audio_bytes
        
    except Exception as e:
        logger.error(f"✗ TTS failed: {str(e)}")
        raise Exception(f"Text-to-speech generation failed: {str(e)}")