Introduction

Our AI model produces high-quality videos of people speaking from text or audio files. The API is designed to be simple and easy to use. You can use the API to create videos of people speaking from text or audio files.

Quickstart

Prerequisite

  • You need a creatify.ai account with API access.
  • You need to go through the Get your API key

Queue a generation task

Generate a video of a person speaking from text.

import requests

url = "https://api.creatify.ai/api/lipsyncs/"

payload = {
    "text": "hello world",
    "creator": "5021bec0-f33f-43e6-b0e3-1cb7f76003c6",
    "aspect_ratio": "1:1"
}
headers = {
    "X-API-ID": "<your-x-api-id>",
    "X-API-KEY": "<your-x-api-key>",
    "Content-Type": "application/json"
}

response = requests.request("POST", url, json=payload, headers=headers)

print(response.text)

Check status

Now our AI model is generating a video of a person speaking from the text you provided. It will return a id of the lipsync item. Then you can check the status of your video generation by sending a GET request to Get lipsync item by id endpoint.

import requests

url = "https://api.creatify.ai/api/lipsyncs/{id}/"

headers = {
    "X-API-ID": "<your-x-api-id>",
    "X-API-KEY": "<your-x-api-key>"
}

response = requests.request("GET", url, headers=headers)

print(response.text)

Once the status is done, you can download the video, the link of the video is in the output field.

Personas

We offer 100+ personas, you can find the full list here.