Gemini Omni Flash picture and sound, always together
On most engines sound is an option; here it is part of the model and there is no switch to turn it off. Of all the ones that generate a track on equal footing with the picture this is the cheapest: 0.27 credits a second, so ten seconds with sound is three credits.
Rendered by this model
Specification
- Built by
- Starts from
- a written brief · your own photo
- Aspect ratios
- 9:16 · 16:9
- Clip length
- 4 / 6 / 8 / 10 s
- Resolution
- 720p
- Sound
- built in, always on
- Reference photos
- 1
- Render time
- about 90s
- Cost
- from 2 to 3 credits per clip
What it is good for
- Sound from the same brief
- A splash, a rustle, room tone — generated with the picture, so they match what is on screen. Nothing here is a track laid under finished footage.
- Three credits for ten seconds
- The same as six seconds on Veo 3.1 Fast, with four more seconds in frame. Veo does not go beyond eight at all.
- A minute and a half
- Faster than Kling, Seedance and Wan. When you are hunting an opening shot, the gap between one minute and two decides how many versions you get through.
When to pick something else
The sound cannot be switched off, so if the material goes under your own music the track has to be stripped in the edit — an engine with a switch is better for that, Veo 3.1 Fast or PixVerse V6. It takes only vertical and landscape, no square and no 4:3. The picture is solid, but for the most expensive shots with glass and moving light full Veo 3.1 leaves it behind.
See every modelHow to brief this model
The things this engine handles differently from the rest. The habits that hold for every model are collected separately, in the help centre.
- Describe the sound in the same sentence as the picture. This engine generates both from one brief, so "the natural sound of pouring" is a condition of the shot here, not an extra.
- Add "no voiceover" if you do not want a voice. Left alone it adds narration nobody approved.
- Use it for a ten-second clip. Three credits for ten seconds with sound is the cheapest longer form on the list.
- Keep to one action in the frame. A dipper being lifted out of honey, a hand setting down a cup — a simple shot comes out convincingly, an elaborate scene less so.
- Choose portrait or landscape. This model has no square, and you can upload at most one photograph as the first frame.
Questions about this model
Other models
- Veo 3.1 FastThe default video engine. The cheapest second among the ones that make sound.
- Veo 3.1The best picture and camera move on the roster. And the priciest second.
- Kling 3 ProHands and objects in motion. For unboxing and for showing a product off.
- Seedance 2.5Nine reference photos. The only engine that holds your product through the shot.
- Seedance 2.0The Seedance picture at two thirds of the price. For clips up to eight seconds.
- Wan 3.0 PrimeTexture up close: cream, fabric, liquid. Five ratios, two credits a clip.
- MiniMax H3 MaxSlow motion and moving material. The highest resolution alongside LTX.
- Grok Imagine 1.5A strong grade and night scenes. For ads that are meant to be loud.
- Happy HorseFood, flowers, interiors. Natural light and a calm frame.
- LTX 2.3The only 1080p on the roster. And one of the two cheapest seconds.
- PixVerse V6One credit a clip. The cheapest video second in the whole studio.
- HeyGen Video AgentThe only engine where somebody speaks Polish. Up to 60 seconds of UGC.
Try this model on your own product
Sign up without a card and get 40 credits. Switching model is one click, so you can send the same brief through several of them and keep the best frame.