Generate top-quality spoken audio in any voice, style and language with the most advanced Text to Speech tool ever. Our AI model renders human intonation and inflections with unprecedented fidelity and it adjusts delivery based on context.

ElevenLabsTextToSpeechAPI.js

const callElevenLabsTextToSpeechAPI = async (text) => {
  if (!text) return "Text parameter can't be null";

  const [rachel, anntoni] = ["21m00Tcm4TlvDq8ikWAM", "ErXwobaYiN019PkySvjV"];

  const url = `https://api.elevenlabs.io/v1/text-to-speech/${rachel}`;

  const apiKey = process.env.ELEVENLABS_KEY;

  const headers = {
    accept: "audio/mpeg",
    "xi-api-key": apiKey,
    "Content-Type": "application/json",
  };

  const data = {
    text,
    model_id: "eleven_monolingual_v1",
    voice_settings: {
      stability: 0.5,
      similarity_boost: 0.5,
    },
  };

  try {
    const response = await fetch(url, {
      method: "POST",
      headers: headers,
      body: JSON.stringify(data),
    });

    if (!response.ok) {
      throw new Error("API request failed");
    }

    const blob = await response.blob();
    const audioUrl = URL.createObjectURL(blob);

    return audioUrl;
  } catch (error) {
    console.error("Error:", error); // Handle any errors
  }
};

export default callElevenLabsTextToSpeechAPI;