Synchronous Voice Cloning
The synchronous voice cloning endpoint allows you to clone a voice and generate speech from text in a single request. This endpoint is ideal for short text content (less than 1000 characters) where you need immediate results.
Endpoint
POST https://aivoiceclonefree.com/api/sync-cloneAuthentication
This endpoint requires authentication using your API key in the Authorization header:
Authorization: Bearer YOUR_API_KEYRequest Parameters
Required Parameters
| Parameter | Type | Description |
|---|---|---|
audio_file | File | The audio sample file for voice cloning (WAV, MP3, M4A formats) |
text | String | The text to be converted to speech using the cloned voice |
Optional Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
speed | Float | 1.0 | Speech speed (0.5 - 2.0) |
pitch | Float | 0.0 | Pitch adjustment (-1.0 to 1.0) |
Audio File Requirements
- Formats: WAV, MP3, M4A
- Duration: 5-30 seconds
- Quality: Clear audio with minimal background noise
- File Size: Maximum 4.5MB
- Content: Natural speech in the target voice
Request Example
cURL
curl -X POST "https://aivoiceclonefree.com/api/sync-clone" \
-H "Authorization: Bearer YOUR_API_KEY" \
-F "audio_file=@voice_sample.wav" \
-F "text=Hello, this is a test of voice cloning technology." \
-F "speed=1.2" \
-F "pitch=0.1"Python
import requests
url = "https://aivoiceclonefree.com/api/sync-clone"
headers = {
"Authorization": "Bearer YOUR_API_KEY"
}
with open("voice_sample.wav", "rb") as audio_file:
files = {
"audio_file": audio_file
}
data = {
"text": "Hello, this is a test of voice cloning technology.",
"speed": 1.2,
"pitch": 0.1
}
response = requests.post(url, headers=headers, files=files, data=data)JavaScript
const formData = new FormData();
formData.append('audio_file', audioFile);
formData.append('text', 'Hello, this is a test of voice cloning technology.');
formData.append('speed', '1.2');
formData.append('pitch', '0.1');
fetch('https://aivoiceclonefree.com/api/sync-clone', {
method: 'POST',
headers: {
'Authorization': 'Bearer YOUR_API_KEY'
},
body: formData
})
.then(response => response.blob())
.then(audioBlob => {
// Handle the audio blob
});Response
Success Response (200 OK)
The response will be an audio file in WAV format containing the generated speech.
Headers:
Content-Type: audio/wavContent-Length: [file_size]
Error Responses
400 Bad Request
{
"detail": "Invalid audio file format. Supported formats: WAV, MP3, M4A"
}401 Unauthorized
{
"detail": "Invalid or missing API key"
}403 Forbidden
{
"detail": "Professional or Unlimited subscription required"
}413 Payload Too Large
{
"detail": "Audio file too large. Maximum size: 4.5MB"
}422 Unprocessable Entity
{
"detail": "Text too long for synchronous processing. Use async endpoint for texts over 1000 characters"
}429 Too Many Requests
{
"detail": "Rate limit exceeded. Please try again later"
}500 Internal Server Error
{
"detail": "Internal server error. Please try again later"
}Usage Limits
- Text Length: Maximum 1000 characters per request
- Audio Duration: 5-30 seconds
- File Size: Maximum 4.5MB
- Rate Limiting: Varies by subscription plan
Best Practices
- Audio Quality: Use high-quality audio samples with clear speech and minimal background noise
- Text Length: Keep text under 1000 characters for optimal performance
- File Format: WAV format generally provides the best results
- Error Handling: Always implement proper error handling for API responses
- Rate Limiting: Respect rate limits and implement exponential backoff for retries
Next Steps
- For longer text content, use the Asynchronous Voice Cloning endpoint
- Learn about error handling best practices
- Explore advanced features and customization options
Last updated on