# Google DeepMind's new video model extends clips to 15 seconds

> Original title: Google's new video model from @GoogleDeepMind

- Source: Replicate
- Published: 2026-11-05T22:09:32.000Z
- Bad Influence: https://badinfluence.news/items/ilmr8yxp0xt1v93ggk0ppucf8
- Original: https://x.com/replicate/status/2118465766856999282

## Summary

Replicate announces Google's new video model from Google DeepMind. The model produces 15-second clips, up from 10, with more natural dialogue and lip-sync, characters that stay consistent across shots, and the ability to edit an existing clip with a new prompt.

## Post

Google's new video model from @GoogleDeepMind

   - 15-second clips, up from 10
   - More natural dialogue and lip-sync
   - Characters stay consistent across shots
   - Edit the same clip with a new prompt

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2118465626117124096%2Fimg%2FH37QIvoO9BCt5I2l.jpg&mode=thumb&exp=1794182400&sig=59a0bd4fbaeb84dc)