Pruna P Video 2 Pro Lipsync

Re-sync the mouth in a talking video to new speech: dub into another language or change a line without a reshoot.

Coming Soon
Video To Video

Pruna P Video 2 Pro Lipsync is coming to Segmind

The playground and serverless API for this model aren't live yet. Here's what we know so far — launch details, pricing, and full API docs will appear on this page.

About

P Video 2 Pro Lipsync is Pruna AI's lip-sync model on the P-Video-2-Pro line. Send a video of someone talking and a new speech track, and get the same video back with the mouth re-synced to the new audio. Use it for dubbing and voice-overs: put a video into another language, or change a line without a reshoot.

What to expect

  • Works best on close-up to medium shots with one speaker whose face is visible.
  • The output keeps your video's resolution and aspect ratio, up to 1080p. Larger videos are scaled down to 1920 px on the long side.
  • A 5 second clip takes about 7 seconds; 15 seconds at 1080p takes about 30.
  • A video in which no face is found fails and is not charged.

Specifications

  • Input: one video of the speaker (up to 200 MB) and one audio track of the new speech.
  • Output: MP4 at 24 fps, as long as the shorter of the video and the audio, up to 60 seconds.
  • Price: per second of returned video, the same at every resolution. A started second counts as a whole one, with a 1 second minimum.

Availability

Launching Thursday 26 November 2026, 18:00 CET.