Skip to main content

Live Portrait

Create lifelike talking head animations from a single image and audio input.

Try it out

Test the Live Portrait API directly in your browser with our interactive playground.

Overview

The Live Portrait API brings still images to life by generating natural head movements and lip synchronization that match the input audio.

API Reference

Endpoint

POST https://api.tryvinci.com/vincilp

Headers

NameTypeDescription
X-User-IDstringRequired. Your user ID

Request Body

Multipart form data with:

ParameterTypeDescription
audioFileAudio file containing speech
imageFilePortrait image to animate

Response

{
url: string, // URL to the generated animation
media_type: string, // "video/mp4"
user_id: string // The user ID used for the request
}

Code Examples

import requests

url = "https://api.tryvinci.com/vincilp"
headers = {"X-User-ID": "your-user-id"}
files = {
"audio": open("speech.wav", "rb"),
"image": open("portrait.jpg", "rb")
}

response = requests.post(url, headers=headers, files=files)
result = response.json()
print(f"Animation URL: {result['url']}")

Input Requirements

Image Requirements
  • Format: JPG, PNG
  • Resolution: 512x512 or higher
  • Clear frontal face portrait
  • Neutral expression recommended
Audio Requirements
  • Format: WAV, MP3, M4A
  • Clear speech with minimal noise
  • Duration: 5-60 seconds optimal
Portrait Guidelines
  • Well-lit, front-facing portrait
  • Neutral background preferred
  • Full face visibility
  • No extreme angles

Best Practices

Image Quality

Use high-resolution portraits with good lighting.

Audio Clarity

Clean audio produces more natural animations.

Optimization

For most natural results, ensure the portrait has good lighting and a neutral expression.