API Documentation

Base URL

Authentication

All API requests require a Bearer token in the Authorization header.

Getting Your API Token

1. Log in to your account dashboard
2. Navigate to API Settings
3. Generate a new API token

Request Header

Authorization: Bearer YOUR_API_TOKEN

Example (cURL)

curl -X GET "https://api.texttospeechai.com/v1/account/" \
  -H "Authorization: Bearer YOUR_API_TOKEN"

Rate Limits

API requests are limited based on your account tier:

Rate limits reset at midnight UTC. Check the X-RateLimit-* headers in API responses.

Generate Speech

Create a new text-to-speech generation request.

Request Body

Example Request

curl -X POST "https://api.texttospeechai.com/v1/generate/" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello, welcome to TextToSpeechAI!",
    "voice": "en_US-kristin-medium",
    "speed": 1.0,
    "format": "mp3"
  }'

Response

{
  "uuid": "abc123-def456-...",
  "status": "pending",
  "text_length": 35,
  "voice": "en_US-kristin-medium",
  "credits_used": 0.35,
  "estimated_time": 5
}

List Voices

Get available voices with optional filtering.

Query Parameters

Example Request

curl "https://api.texttospeechai.com/v1/voices/?language=en&gender=female" \
  -H "Authorization: Bearer YOUR_API_TOKEN"

Check Status

Check the status of a generation request.

Status Values

• pending - Request queued for processing
• processing - Currently generating audio
• completed - Audio ready for download
• failed - Generation failed (see error field)

Response (Completed)

{
  "uuid": "abc123-def456-...",
  "status": "completed",
  "audio_url": "https://texttospeechai.com/uploads/generations/...",
  "duration_seconds": 2.5,
  "processing_time_ms": 1200
}

Voice Cloning

Create a cloned voice from reference audio.

Request (multipart/form-data)

Example Request

curl -X POST "https://api.texttospeechai.com/v1/clone/" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -F "name=My Custom Voice" \
  -F "audio=@reference.wav" \
  -F "language=en"

Account Info

Get account information and credit balance.

Response

{
  "email": "user@example.com",
  "credits": 1000.00,
  "created_at": "2024-01-01T00:00:00Z",
  "rate_limit": {
    "limit": 100,
    "remaining": 95,
    "used": 5,
    "resets_at": "2024-01-02T00:00:00Z"
  }
}

Error Codes

Error Response Format

{
  "error": "error_description"
}

Frequently Asked Questions

Code Examples

• Python
• JavaScript
• cURL

import requests
import time

API_KEY = "YOUR_API_TOKEN"
BASE_URL = "https://api.texttospeechai.com/v1"

headers = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json"
}

# Generate speech
response = requests.post(
    f"{BASE_URL}/generate/",
    headers=headers,
    json={
        "text": "Hello, world!",
        "voice": "en_US-kristin-medium",
        "format": "mp3"
    }
)

data = response.json()
uuid = data["uuid"]

# Poll for completion
while True:
    status = requests.get(
        f"{BASE_URL}/status/{uuid}/",
        headers=headers
    ).json()

    if status["status"] == "completed":
        print(f"Audio URL: {status['audio_url']}")
        break
    elif status["status"] == "failed":
        print(f"Error: {status['error']}")
        break

    time.sleep(2)

const API_KEY = 'YOUR_API_TOKEN';
const BASE_URL = 'https://api.texttospeechai.com/v1';

async function generateSpeech(text, voice) {
  const response = await fetch(`${BASE_URL}/generate/`, {
    method: 'POST',
    headers: {
      'Authorization': `Bearer ${API_KEY}`,
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({
      text: text,
      voice: voice,
      format: 'mp3'
    })
  });

  const data = await response.json();

  // Poll for completion
  while (true) {
    const status = await fetch(
      `${BASE_URL}/status/${data.uuid}/`,
      { headers: { 'Authorization': `Bearer ${API_KEY}` } }
    ).then(r => r.json());

    if (status.status === 'completed') {
      return status.audio_url;
    } else if (status.status === 'failed') {
      throw new Error(status.error);
    }

    await new Promise(r => setTimeout(r, 2000));
  }
}

// Usage
generateSpeech('Hello, world!', 'en_US-kristin-medium')
  .then(url => console.log('Audio URL:', url))
  .catch(err => console.error(err));

# Generate speech
curl -X POST "https://api.texttospeechai.com/v1/generate/" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello, world!", "voice": "en_US-kristin-medium"}'

# Check status (replace UUID)
curl "https://api.texttospeechai.com/v1/status/abc123-def456/" \
  -H "Authorization: Bearer YOUR_API_TOKEN"

# List voices
curl "https://api.texttospeechai.com/v1/voices/?language=en" \
  -H "Authorization: Bearer YOUR_API_TOKEN"