benchrAll capabilities Image, audio and video
Generate video from a prompt or a still
Text or an image goes in, a short video comes out - and on one of the two documented models, with native audio.
DocsDocumented in partTestNot tested by benchr
Gemini API
Overview
- Turns text prompts and images into short videos on Gemini Omni Flash, which the documentation names as the default recommendation.
- Generates video with native audio on Veo 3.1.
- Takes a still image as the starting frame, which is the reliable way to control composition.
How it works
- 01Start from an image you already like rather than from text alone. Composition control is the hard part.
- 02Write the shot, not the story: one camera move, one subject action, one lighting state.
- 03Generate several short clips and cut them, instead of asking for one long take.
- 04Budget for iteration - this is the least steerable capability on this list.
Limits
- The vendor page benchr read documents the capability and the two models but publishes no output length, resolution or rate limits on that page.
- Because those limits are undocumented on the page checked, treat any figure you have seen elsewhere as unverified.
- Native audio is documented for Veo 3.1 only, not for the default model.
Verification
benchr test runs
benchr has not run this capability. No test has been published.
benchr test runs →
Evidence
Sources
- Google - Gemini video generation: Gemini Omni Flash and Veo 3.1 Tier 1 · September 1, 2026
Not stated by the source
- Maximum clip length
- Output resolution and frame rate
- Per-generation pricing or quota
Source-check history
- September 1, 2026DocsDocumented in partFirst logged as documented in part: the page names the two models and the capability but publishes no length, resolution or rate limits, so those stay in the not-stated-by-the-source list rather than being filled from memory.