The Elevenlabs8 API provides a simple interface to state-of-the-art audio models and features. Follow this guide to learn how to create lifelike speech with our Text to Speech API using direct HTTP requests.

​
Using the Text to Speech API

1

Create an API key

Create an API key in the dashboard here, which you’ll use to securely access the API.Store the key as a managed secret and pass it in the X-API-KEY header with your requests.
.env
ELEVENLABS8_API_KEY=<your_api_key_here>
2

Make your first request

Create a new file named example.py or example.js, depending on your language of choice and add the following code:
3

Run the code

You should see “Audio generated successfully!” with the History ID and Audio URL, then find an output.mp3 file in your directory.

​
Request Format

All API requests to TTSLab should include the X-API-KEY header with your API key: 
X-API-KEY: your_api_key_here

​
Model Versions

TTSLab supports different model versions with different request formats:

​
v3 Models

Use the simplified inputs format with model_id: 
{
  "inputs": [
      {
        "text": "The first move is what sets everything in motion.",
        "voice_id": "JBFqnCBsd6RMkjVDRZzb"
      },
      {
        "text": "The second move is what sets everything in motion.",
        "voice_id": "2EiwWnXFnvU5JabPnv8n"
      },
  ],
  "model_id": "eleven_v3"
}

​
v1/v2 Models

Use the traditional format with additional parameters and config: 
{
  "text": "Your text here",
  "voice_id": "voice_id_here",
  "model_id": "eleven_flash_v2_5",
  "config": {
    "stability": 0.5,
    "similarity_boost": 0.75,
    "style": 0.0,
    "use_speaker_boost": true
  }
}
Config Parameters:
  • stability (0.0 - 1.0): Controls voice consistency
  • similarity_boost (0.0 - 1.0): Controls voice similarity to original
  • style (0.0 - 1.0): Controls speaking style
  • use_speaker_boost (boolean): Enhances speaker clarity

​
Response Handling

The API returns a JSON object with the following structure: 
{
  "id": "history_id_here",
  "user": {
    "fullname": "User Full Name",
    "avatar": "https://api.elevenlabs8.com/media/avatars/user.jpg"
  },
  "history_id": "unique_history_id",
  "prompt": "The first move is what sets everything in motion.",
  "model": "ttslab_multilingual_v3",
  "voice": "voice_name_here",
  "config": {
    "stability": 0.5,
    "similarity_boost": 0.75,
    "style": 0.0,
    "use_speaker_boost": true
  },
  "credits_used": 1,
  "status": "completed",
  "shared_url": "https://app.elevenlabs8.com/share/audio_id",
  "created_at": "2024-01-01T12:00:00Z",
  "audio_url": "https://api.elevenlabs8.com/media/audio/output.mp3"
}

​
Response Fields:

  • id: Unique identifier for the history record
  • user: User information (fullname, avatar)
  • history_id: History tracking ID
  • prompt: The text that was converted to speech
  • model: Model used for generation
  • voice: Voice used for generation
  • config: Configuration parameters used
  • credits_used: Number of credits consumed
  • status: Status of the generation (completed, processing, failed)
  • shared_url: Public shareable URL for the audio
  • created_at: Timestamp of creation
  • audio_url: Direct URL to download the generated audio file

​
Downloading the Audio:

To get the actual audio file, make a GET request to the audio_url: 
# Download the audio file
audio_response = requests.get(response.json()["audio_url"])
with open("output.mp3", "wb") as f:
    f.write(audio_response.content)

​
Next Steps