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

P-Video-2

Premium AI video generation from text, images, and audio — up to 20 seconds at 720p or 1080p.

Inference

Varies by length

Per second

$0.025–$0.05/s

720p / 1080p

Output

Up to 20s · 720p / 1080p

Billed per second of the finished video. 720p is $0.025/s ($0.015/s draft); 1080p is $0.05/s ($0.03/s draft).

  • Same inputs as P-Video: text, image, and optional audio.
  • Duration 1–20s, or leave it empty and the model picks length from the prompt.
  • Optional last-frame reference; 24 or 48 fps; cheaper draft previews.
Learn moreSign up

Image (optional)

No image selected yet

Audio (optional)

No audio selected yet

Output

Loading quota…