Lipsync/talk-photo
Create realistic talking avatars from photos for demos, presentations, and content creation.
Output: $0.002 / second or 500 seconds / $1
Input
avatar * image
Image url address
input image
speech * audio
Audio url address
Audio File
disable_safety_checker boolean
Note: The website version of this model always runs with safety checks enabled. For details,see VModel's platform safety guidelines..
Disable safety checker for generated images
Reset
Output
{
  "task_id": "d9oo2z1s89lobg8oz5",
  "user_id": 1,
  "version": "d833e9a0a97b66096f9741fee5368ee1c53bda61d569f53f1b24c106c867157c",
  "error": null,
  "total_time": 37,
  "predict_time": 37,
  "logs": null,
  "output": [
    "https://vmodel.ai/data/model/lipsync/talk-photo/result_demo.mp4"
  ],
  "status": "succeeded",
  "create_at": 1746492954,
  "completed_at": 1746493015,
  "input": {
    "avatar": "https://vmodel.ai/data/model/lipsync/talk-photo/talk-photo-input.jpg",
    "speech": "https://vmodel.ai/data/model/lipsync/talk-photo/examples_wav_talk_male_law_10s.wav",
    "disable_safety_checker": false
  }
}
Generated in: 37 seconds
Download
Examples
Pricing
Model pricing for lipsync/talk-photo. Looking for volume pricing? Get in touch.
When
āš™ using this model
$0.0020
per second of input audio
or 500 seconds for $1
Readme

Loading...