image-to-videotext-to-videoaudio-to-video

P-Video-Avatar

Generate talking-head avatar videos from one image with script or uploaded audio.

Inference

1.83s

Per second

$0.025/s

Output

720p / 1080p

Typical API runs; actual latency and pricing may vary.

  • Strong lip-sync with multilingual voice and language controls.
  • Supports portrait and landscape outputs by matching the input image format.
Learn moreSign up

Image (required)

Audio (optional)

Output

Loading quota…