Text To Speech

curl -X GET "https://api.heygen.com/v1/audio/voices" \
  -H "X-Api-Key: $HEYGEN_API_KEY"

curl -X GET "https://api.heygen.com/v1/audio/voices" \
  -H "X-Api-Key: $HEYGEN_API_KEY"

interface TTSVoice {
  voice_id: string;
  language: string;
  gender: "female" | "male" | "unknown";
  name: string;
  preview_audio_url: string | null;
  support_pause: boolean;
  support_locale: boolean;
  type: string;
}

interface TTSVoicesResponse {
  error: null | string;
  data: {
    voices: TTSVoice[];
  };
}

async function listTTSVoices(): Promise<TTSVoice[]> {
  const response = await fetch("https://api.heygen.com/v1/audio/voices", {
    headers: { "X-Api-Key": process.env.HEYGEN_API_KEY! },
  });

  const json: TTSVoicesResponse = await response.json();

  if (json.error) {
    throw new Error(json.error);
  }

  return json.data.voices;
}

import requests
import os

def list_tts_voices() -> list:
    response = requests.get(
        "https://api.heygen.com/v1/audio/voices",
        headers={"X-Api-Key": os.environ["HEYGEN_API_KEY"]}
    )

    data = response.json()
    if data.get("error"):
        raise Exception(data["error"])

    return data["data"]["voices"]

{
  "error": null,
  "data": {
    "voices": [
      {
        "voice_id": "f38a635bee7a4d1f9b0a654a31d050d2",
        "name": "Chill Brian",
        "language": "English",
        "gender": "male",
        "preview_audio_url": "https://resource.heygen.ai/text_to_speech/WpSDQvmLGXEqXZVZQiVeg6.mp3",
        "support_pause": true,
        "support_locale": false,
        "type": "public"
      }
    ]
  }
}

curl -X POST "https://api.heygen.com/v1/audio/text_to_speech" \
  -H "X-Api-Key: $HEYGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello! Welcome to our product demo.",
    "voice_id": "YOUR_VOICE_ID",
    "speed": 1.0
  }'

interface TTSRequest {
  text: string;
  voice_id: string;
  speed?: number;
  pitch?: number;
  locale?: string;
  elevenlabs_settings?: {
    model?: string;
    similarity_boost?: number;
    stability?: number;
    style?: number;
  };
}

interface WordTimestamp {
  word: string;
  start: number;
  end: number;
}

interface TTSResponse {
  error: null | string;
  data: {
    audio_url: string;
    duration: number;
    request_id: string;
    word_timestamps: WordTimestamp[];
  };
}

async function textToSpeech(request: TTSRequest): Promise<TTSResponse["data"]> {
  const response = await fetch(
    "https://api.heygen.com/v1/audio/text_to_speech",
    {
      method: "POST",
      headers: {
        "X-Api-Key": process.env.HEYGEN_API_KEY!,
        "Content-Type": "application/json",
      },
      body: JSON.stringify(request),
    }
  );

  const json: TTSResponse = await response.json();

  if (json.error) {
    throw new Error(json.error);
  }

  return json.data;
}

import requests
import os

def text_to_speech(
    text: str,
    voice_id: str,
    speed: float = 1.0,
    pitch: int = 0,
    locale: str | None = None,
) -> dict:
    payload = {
        "text": text,
        "voice_id": voice_id,
        "speed": speed,
        "pitch": pitch,
    }

    if locale:
        payload["locale"] = locale

    response = requests.post(
        "https://api.heygen.com/v1/audio/text_to_speech",
        headers={
            "X-Api-Key": os.environ["HEYGEN_API_KEY"],
            "Content-Type": "application/json",
        },
        json=payload,
    )

    data = response.json()
    if data.get("error"):
        raise Exception(data["error"])

    return data["data"]

{
  "error": null,
  "data": {
    "audio_url": "https://resource2.heygen.ai/text_to_speech/.../id=365d46bb.wav",
    "duration": 5.526,
    "request_id": "p38QJ52hfgNlsYKZZmd9",
    "word_timestamps": [
      { "word": "<start>", "start": 0.0, "end": 0.0 },
      { "word": "Hey", "start": 0.079, "end": 0.219 },
      { "word": "there,", "start": 0.239, "end": 0.459 },
      { "word": "<end>", "start": 5.526, "end": 5.526 }
    ]
  }
}

const result = await textToSpeech({
  text: "Welcome to our quarterly earnings call.",
  voice_id: "YOUR_VOICE_ID",
});

console.log(`Audio URL: ${result.audio_url}`);
console.log(`Duration: ${result.duration}s`);

const result = await textToSpeech({
  text: "We're thrilled to announce our newest feature!",
  voice_id: "YOUR_VOICE_ID",
  speed: 1.1,
});

const result = await textToSpeech({
  text: "Bem-vindo ao nosso produto.",
  voice_id: "MULTILINGUAL_VOICE_ID",
  locale: "pt-BR",
});

async function generateSpeech(text: string, language: string): Promise<string> {
  const voices = await listTTSVoices();
  const voice = voices.find(
    (v) => v.language.toLowerCase().includes(language.toLowerCase())
  );

  if (!voice) {
    throw new Error(`No TTS voice found for language: ${language}`);
  }

  const result = await textToSpeech({
    text,
    voice_id: voice.voice_id,
  });

  return result.audio_url;
}

const audioUrl = await generateSpeech("Hello and welcome!", "english");

word <break time="1s"/> word