backend/tts.py

import io
import os
import struct

from google import genai
from google.genai import types


def _make_wav(pcm_data: bytes, sample_rate: int = 24000, channels: int = 1, bits_per_sample: int = 16) -> bytes:
    """Wrap raw PCM bytes in a WAV container."""
    data_size = len(pcm_data)
    byte_rate = sample_rate * channels * bits_per_sample // 8
    block_align = channels * bits_per_sample // 8

    buf = io.BytesIO()
    # RIFF header
    buf.write(b"RIFF")
    buf.write(struct.pack("<I", 36 + data_size))
    buf.write(b"WAVE")
    # fmt chunk
    buf.write(b"fmt ")
    buf.write(struct.pack("<I", 16))  # chunk size
    buf.write(struct.pack("<H", 1))   # PCM format
    buf.write(struct.pack("<H", channels))
    buf.write(struct.pack("<I", sample_rate))
    buf.write(struct.pack("<I", byte_rate))
    buf.write(struct.pack("<H", block_align))
    buf.write(struct.pack("<H", bits_per_sample))
    # data chunk
    buf.write(b"data")
    buf.write(struct.pack("<I", data_size))
    buf.write(pcm_data)
    return buf.getvalue()


def generate_speech(text: str) -> bytes:
    """Generate speech audio from text using Gemini TTS.

    Args:
        text: The text to convert to speech.

    Returns:
        WAV audio bytes ready to play in a browser.
    """
    client = genai.Client(api_key=os.getenv("GOOGLE_API_KEY"))

    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",
                    )
                ),
            ),
        ),
    )

    audio_data = response.candidates[0].content.parts[0].inline_data.data
    return _make_wav(audio_data)