Gemini Omni Flash outputs 24 FPS: conform to 25 or 30 with Sume
The Gemini API model card lists 24 FPS for Omni Flash output. If your timeline is 25, 30 or 60, Sume's video trim can conform it with an output fps field.

Google's model card for Gemini Omni Flash lists video output at 360p, 720p, 1080p and 4K at 24 FPS (read 2026-10-02). If your edit timeline runs at 25, 30 or 60, a 24 FPS clip needs conforming. On Sume, the video trim endpoint accepts an output.fps of 24, 25, 30 or 60 and re-encodes the clip.
What Google lists
The model card gives the stable id gemini-omni-1.1-flash, a preview id, inputs of text, image and video up to 10 seconds for editing and extension, and output durations of 3 to 10 seconds (Gemini API docs, read 2026-10-02).
| Item | Value |
|---|---|
| Resolutions | 360p, 720p, 1080p, 4K |
| Frame rate | 24 FPS |
| Duration | 3s to 10s |
| Latest update | August 2026 |
Why 24 matters
Mixing 24 FPS footage into a 30 FPS timeline causes the editor to repeat or blend frames. If everything else in your project is 25 or 30, conform once, up front, instead of per export.
Conform on Sume
Video trim cuts a range out of one Sume-hosted clip into a new MP4. Its optional output field takes { width, height, fps } with fps of 24, 25, 30 or 60, and conforming works with precision: "exact", the default frame-accurate re-encode (Video trim). Omit output and the clip inherits the source.
The source must be a media.sume.com artifact, so a clip generated on Sume qualifies; off-host URLs are rejected until you import them. An Idempotency-Key is required on the call.
curl -X POST https://api.sume.com/v1/video-trim \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: conform-001" \
-d '{"video_url": "https://media.sume.com/artifacts/artf_demo/clip.mp4", "start": 0, "duration": 8, "output": {"width": 1920, "height": 1080, "fps": 30}}'Limits to know
Conforming changes the frame count, not the motion the model drew, so it will not smooth a 24 FPS look into true 30. Trim's docs list a public rate of $0.02 per job and say to confirm it in the live catalog. If you do not need a cut, set start to 0 and duration to the clip length.
Sources
Related posts
More in Media tools
- Gemini video understanding: 100 vs 300 tokens a second vs Sume
Gemini reads video at about 100 tokens a second, or 300 at high resolution: 60,000 or 180,000 tokens for 10 minutes. How Sume's stills route compares.
- Hook, demo, CTA: assemble a product ad from 3 clips in one render
Build a 15-second holiday product ad from a hook clip, a demo clip and a call-to-action card with one Sume timeline render. Plan first, render second.
- hypit boundaries: cut candidates and the 0.1 threshold
hypit boundaries scores possible cuts from a 12 fps 32x32 difference pass. What rate and threshold do, and how it differs from reference ingest's shot list.
- Word-level transcript with confidence scores: hypit transcribe
hypit transcribe returns each word with start, end and a 0-1 score using WhisperX, or Sume STT 1.0 without scores. Engines, checkpoints, billing and errors.
Written by Sume