TTS logic for Listen Better demo

tts.ts

...

async function convertAudioContentToMp3(
  audioContent: GeminiTTSAudioContent,
  opts?: { workDir?: string; baseName?: string }
): Promise<string> {
  if (!audioContent || !audioContent.data) {
    throw new Error('No audio content provided');
  }

  const mimeType = audioContent.mimeType;
  const audioPcmData = audioContent.data;

  const pcmBuffer = Buffer.from(audioPcmData, 'base64');

  // Parse MIME type like: audio/L16;codec=pcm;rate=24000
  let parsedSampleRate = 24000;
  let parsedBitDepth = 16;
  if (typeof mimeType === 'string') {
    const rateMatch = mimeType.match(/(?:^|[;\s])rate=(\d+)/i);
    const depthMatch = mimeType.match(/^audio\/L(\d+)/i);
    if (rateMatch)
      parsedSampleRate = parseInt(rateMatch[1], 10) || parsedSampleRate;
    if (depthMatch)
      parsedBitDepth = parseInt(depthMatch[1], 10) || parsedBitDepth;
  }
  const outputDir = opts?.workDir || os.tmpdir();
  const baseName = opts?.baseName || `dialogue_${Date.now()}`;
  await pcmBufferToMp3(pcmBuffer, outputDir, baseName, {
    sampleRate: parsedSampleRate,
    channels: 1,
    bitrate: '192k',
    codec: 'libmp3lame',
    bitDepth: parsedBitDepth,
  });
  console.log(`[convertAudioContentToMp3] MP3 written to ${outputDir}/${baseName}.mp3 (${audioContent.data.length} bytes)`);

  return `${outputDir}/${baseName}.mp3`;
}