Skip to main content
POST
/
tts
/
voice-clone
Voice Cloning
curl --request POST \
  --url https://api.example.com/tts/voice-clone \
  --header 'Content-Type: application/json' \
  --data '
{
  "text": "<string>",
  "language": "<string>",
  "api_key": "<string>"
}
'

​
Overview

Generate speech that mimics a specific voice by providing a reference audio sample. This allows you to create custom voices for your applications.

​
Request Body

This endpoint uses multipart/form-data for file uploads.
​
reference_audio
file
required
Reference audio file (WAV format) containing the voice to clone. Should be 3-10 seconds of clear speech.
​
text
string
required
The text to convert to speech using the cloned voice
​
language
string
default:"en"
Language code (e.g., “en”, “es”, “fr”)
​
api_key
string
required
Your GistMag API key

​
Example Request

curl -X POST https://api.gistmag.co.uk/tts/voice-clone \
  -F "reference_audio=@reference.wav" \
  -F "text=Hello, this is a test using a cloned voice." \
  -F "language=en" \
  -F "api_key=your_api_key_here" \
  --output output.wav

​
Reference Audio Requirements

  • Format: WAV (recommended) or MP3
  • Duration: 3-10 seconds
  • Quality: Clear speech, minimal background noise
  • Content: Should contain natural speech in the target language
Ensure you have permission to use the reference audio for voice cloning. Respect privacy and copyright laws.

​
Response

The response is an audio file (WAV format) with the generated speech using the cloned voice. Content-Type: audio/wav Content-Disposition: attachment; filename=output.wav

​
Example Usage

​
Python

import requests

with open("reference.wav", "rb") as f:
    files = {"reference_audio": f}
    data = {
        "text": "Hello, this is a test.",
        "language": "en",
        "api_key": "your_api_key_here"
    }
    
    response = requests.post(
        "https://api.gistmag.co.uk/tts/voice-clone",
        files=files,
        data=data
    )

with open("output.wav", "wb") as f:
    f.write(response.content)

​
JavaScript

const formData = new FormData();
formData.append('reference_audio', referenceAudioFile);
formData.append('text', 'Hello, this is a test.');
formData.append('language', 'en');
formData.append('api_key', 'your_api_key_here');

const response = await fetch('https://api.gistmag.co.uk/tts/voice-clone', {
  method: 'POST',
  body: formData
});

const audioBlob = await response.blob();
const audioUrl = URL.createObjectURL(audioBlob);

​
Streaming with Voice Clone

For streaming audio with voice cloning, use the /tts/stream/voice-clone endpoint.
Voice cloning works best with clear, high-quality reference audio. The model learns the voice characteristics from the reference sample.