Gemini Omni store=false sync video vs Sume's 30-second sync cap
Gemini suggests background=false, store=false, stream=false for synchronous video. Sume sync mode waits at most 30 seconds, then you poll status_url.

The Gemini Omni guide recommends background=false, store=false and stream=false for faster, synchronous unary generation, noting that store=false means the video cannot be edited later with previous_interaction_id. Sume has a synchronous mode too, but it is a bounded wait: wait_timeout_seconds is clamped to 0..30, and video jobs usually outlast it.
Sources: the Gemini Omni guide and Sume's Jobs and results, read 2026-10-01.
What does Gemini's synchronous setting trade away?
With store=false the generated video is not editable in later turns through previous_interaction_id. That is the cost the guide names for the faster path.
How long does Sume sync mode wait?
At most 30 seconds, and less when waiter capacity is unavailable. The cap bounds how long the HTTP request blocks, not how long the job may take. Image jobs often finish inside it; the docs say video, avatar-video and face-swap jobs routinely do not.
| Aspect | Gemini Omni | Sume |
|---|---|---|
| Synchronous option | background=false, store=false, stream=false | mode: "sync" with wait_timeout_seconds |
| Wait bound | Not stated in this guide | Clamped to 0..30 seconds |
| Follow-up edits | Lost with store=false | Not tied to the wait mode |
What happens when the 30 seconds run out?
The response is still 2xx and carries the job id, plus status_url, result_url, events_url, cancel_url and a sync object whose timed_out is true. Continue with GET status_url, honoring next_poll_after_seconds. Do not submit a new paid job for the same intent; if you retry the submit, reuse the same Idempotency-Key.
sync is null on async and webhook responses. For the details of the timeout case, see this guide.
Which mode should I use for video?
The docs call sync the wrong tool for anything that can outlast 30 seconds. Submit with async and poll, or use webhook, and keep the wait in your client.
Sources
Related posts
More in Developers
- Gemini Omni task values mapped to Sume request fields
Google's Omni task field takes text_to_video, image_to_video, reference_to_video, edit or extend. On Sume the fields you send pick the mode; extend is absent.
- Gemini TTS caps 200 voices per project: picking a voice on Sume
Gemini TTS stores at most 200 voices per project for a year. On Sume you list avatars and use one whose voice.status is ready, with no stored-voice quota.
- Text to speech mulaw 8000 Hz: Gemini 3.8 and Sume TTS
Sume TTS can return pcm_mulaw or pcm_alaw at 8000 Hz in wav or raw containers. Gemini 3.8 TTS does it with audio/mulaw and audio/alaw mime types.
- Gemini TTS voice design voice_ id vs Sume voice ids
Gemini voice design returns a persistent voice_ id from a text prompt. Sume TTS accepts only a voice UUID or voi_ library id, and rejects other shapes with 400.
Written by Sume