Function synthesizeWithElevenLabs

apps/sim/app/api/tools/tts/unified/route.ts:433–487

(
  params: ElevenLabsTtsUnifiedParams
)

}

async function synthesizeWithElevenLabs(
  params: ElevenLabsTtsUnifiedParams
): Promise<{ audioBuffer: Buffer; format: string; mimeType: string }> {
  const {
    text,
    apiKey,
    voiceId,
    modelId = 'eleven_turbo_v2_5',
    stability = 0.5,
    similarityBoost = 0.8,
    style,
    useSpeakerBoost = true,
  } = params

  const voiceSettings: any = {
    stability: Math.max(0, Math.min(1, stability)),
    similarity_boost: Math.max(0, Math.min(1, similarityBoost)),
    use_speaker_boost: useSpeakerBoost,
  }

  if (style !== undefined) {
    voiceSettings.style = Math.max(0, Math.min(1, style))
  }

  const response = await fetch(`https://api.elevenlabs.io/v1/text-to-speech/${voiceId}`, {
    method: 'POST',
    headers: {
      Accept: 'audio/mpeg',
      'Content-Type': 'application/json',
      'xi-api-key': apiKey,
    },
    body: JSON.stringify({
      text,
      model_id: modelId,
      voice_settings: voiceSettings,
    }),
  })

  if (!response.ok) {
    const error = await readTtsErrorJson(response, 'ElevenLabs TTS error response')
    const errorMessage = getTtsErrorMessage(error, response.statusText)
    throw new Error(`ElevenLabs TTS API error: ${errorMessage}`)
  }

  const audioBuffer = await readResponseToBufferWithLimit(response, {
    maxBytes: MAX_TTS_AUDIO_BYTES,
    label: 'ElevenLabs TTS audio response',
  })

  return {
    audioBuffer,
    format: 'mp3',
    mimeType: 'audio/mpeg',
  }
}

async function synthesizeWithCartesia(
  params: Partial<CartesiaTtsParams>