Text-to-Speech

Convert Text to Speech

Convert text to speech using TTSLab’s advanced AI models.

curl -X POST "https://api.elevenlabs8.com/api/tts/audio-generate/" \
  -H "X-API-KEY: your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "inputs": [
      {
        "text": "Hello, this is a test message.",
        "voice_id": "JBFqnCBsd6RMkjVDRZzb"
      },
      {
        "text": "Hello, this is a test message.",
        "voice_id": "JBFqnCBsd6RMkjVDRZzb"
      }
    ],
    "model_id": "eleven_v3"
  }'

import requests

url = "https://api.elevenlabs8.com/api/tts/audio-generate/"
headers = {
    "X-API-KEY": "your_api_key_here",
    "Content-Type": "application/json"
}

# For v3 models
data = {
    "inputs": [
      {
          "text": "Hello, this is a test message.",
          "voice_id": "JBFqnCBsd6RMkjVDRZzb"
      },
      {
          "text": "Hello, this is a test message.",
          "voice_id": "JBFqnCBsd6RMkjVDRZzb"
      }
    ],
    "model_id": "eleven_v3"
}

# For v1/v2 models
# data = {
#     "text": "Hello, this is a test message.",
#     "voice_id": "JBFqnCBsd6RMkjVDRZzb",
#     "model_id": "eleven_flash_v2_5",
#     "config": {
#         "stability": 0.5,
#         "similarity_boost": 0.75,
#         "style": 0.0,
#         "use_speaker_boost": true
#     }
# }

response = requests.post(url, headers=headers, json=data)
print(response.json())

const fetch = require('node-fetch');

const url = 'https://api.elevenlabs8.com/api/tts/audio-generate/';
const headers = {
    'X-API-KEY': 'your_api_key_here',
    'Content-Type': 'application/json'
};

// For v3 models
const data = {
    inputs: {
        text: 'Hello, this is a test message.',
        voice_id: 'JBFqnCBsd6RMkjVDRZzb'
    },
    model_id: 'eleven_v3'
};

// For v1/v2 models
// const data = {
//     text: 'Hello, this is a test message.',
//     voice_id: 'JBFqnCBsd6RMkjVDRZzb',
//     model_id: 'eleven_flash_v2_5',
//     config: {
//         stability: 0.5,
//         similarity_boost: 0.75,
//         style: 0.0,
//         use_speaker_boost: true
//     }
// };

fetch(url, {
    method: 'POST',
    headers: headers,
    body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data));

Request Parameters

v3 Models

Parameter	Type	Required	Description
inputs.text	string	Yes	Text to convert to speech
inputs.voice_id	string	Yes	Voice ID to use
model_id	string	Yes	Model ID (e.g., “eleven_v3”)

v1/v2 Models

Parameter	Type	Required	Description
text	string	Yes	Text to convert to speech
voice_id	string	Yes	Voice ID to use
model_id	string	Yes	Model ID (e.g., “eleven_flash_v2_5”)
config	object	No	Voice configuration settings

Config Parameters (v1/v2 only)

Parameter	Type	Range	Description
stability	float	0.0 - 1.0	Controls voice consistency
similarity_boost	float	0.0 - 1.0	Controls voice similarity to original
style	float	0.0 - 1.0	Controls speaking style
use_speaker_boost	boolean	-	Enhances speaker clarity

Response

{
  "success": true,
  "data": {
    "id": "history_id_123",
    "user": {
      "fullname": "John Doe",
      "avatar": "https://api.elevenlabs8.com/media/avatars/john.jpg"
    },
    "history_id": "unique_history_id",
    "prompt": "Hello, this is a test message.",
    "model": "eleven_v3",
    "voice": "Rachel",
    "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"
  },
  "message": "Audio generated successfully"
}

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()["data"]["audio_url"])
with open("output.mp3", "wb") as f:
    f.write(audio_response.content)

Error Responses

{
  "success": false,
  "error": {
    "code": "INVALID_VOICE_ID",
    "message": "Voice ID not found"
  }
}

Common Error Codes

Code	Description
INVALID_API_KEY	Invalid or missing API key
INVALID_VOICE_ID	Voice ID not found
INVALID_MODEL_ID	Model ID not found
TEXT_TOO_LONG	Text exceeds maximum length
INSUFFICIENT_CREDITS	Not enough credits
RATE_LIMIT_EXCEEDED	Rate limit exceeded