Find any model, tool or page and jump to it.
P-Video Avatar is Pruna AI's purpose-built talking-head video model. Upload one photo of a person. Attach an audio track, or type the words and pick one of thirty built-in voices. The voices speak ten languages, so you can publish one script in ten markets. P-Video Avatar renders the person speaking, with lip shapes, expression, and timing matched to the speech. A short note on tone steers the delivery. A short note on behavior steers the picture. Render at 720p while you iterate, then render the final take at 1080p. Available in Visual Sandbox alongside other advanced AI video models, so you can generate, edit, and iterate in a single place. A natural fit for UGC ads, product demos, explainer hosts, course intros, and localized versions of one script.
| Tier | Price |
|---|---|
| 720p | $0.04/s |
| 1080p | $0.06/s |
Billed per second of finished video. The clip is as long as the speech. Nothing in the request states that length. Visual Sandbox reserves credit for a full minute and then charges only the delivered length.