Sora and Google Veo: camera docs compared
The docs of Sora and Google Veo part on 4 of the six camera points: framing, cuts, frames and negative prompt. They read alike on camera moves and motion amount. As of 2026-09-25.
| Field | Sora | Google Veo |
|---|---|---|
| How a camera move is asked for | Words in the prompt | Words in the prompt |
| Shot sizes and angles in the docs | Shown in examples | Defined in a glossary |
| Cuts inside one generation | Several shots per clip | Editing terms only |
| Start and end frames | First frame only | First and last frame |
| A negative prompt | None in the docs | A negative prompt field |
| A setting for how much the picture moves | None in the docs | None in the docs |
Inclusion rule. The six points every model on the register is read on. Order. The order the points take on every model page.
1How the two differ
Sora reads “Several shots per clip” on cuts inside a clip, while Google Veo reads “Editing terms only” on cuts inside a clip. Sora reads “First frame only” on start and end frames, while Google Veo reads “First and last frame” on start and end frames. Only Google Veo documents a negative prompt field. Sora's docs use 10 of the site's camera words and Google Veo's use 25, sharing tilt, dolly, handheld and aerial shot.
2The differing points, in the docs' words
Shot sizes and angles in the docs
Weak Camera shot: cinematic look Strong Camera shot: wide shot, low angle
OpenAI Cookbook, Sora 2 prompting guide
Close-up : frames the subject tightly, typically focusing on the face to emphasize emotions or a specific detail.
Google Cloud, Veo video prompt guide
Cuts inside one generation
Optimized Shot List ( 2 shots / 4 s total)
OpenAI Cookbook, Sora 2 prompting guide
You can use cinematic terms for editing style and specific techniques.
Google Cloud, Veo video prompt guide
Start and end frames
The model uses the image as an anchor for the first frame, while your text prompt defines what happens next.
OpenAI Cookbook, Sora 2 prompting guide
First and last frames to video
Google Cloud, Veo video prompt guide
A negative prompt
Sora: the docs read do not cover this.
Negative prompts are a tool that helps specify the elements that you don't want generated in your video.
Google Cloud, Veo video prompt guide
- Camera directionThe guide asks for a stated framing and shows weak and strong ways to write it
- Camera angles and shot typesShot sizes and angles are defined one by one, from extreme close-up to wide, low-angle and dutch angle
- Worked exampleIts worked example is a shot list: two timed shots inside one four-second clip
- Cinematic termsEditing terms such as match cut, jump cut and montage can be named in the prompt
- Image inputAn input image anchors the first frame; the prompt says what happens next
- Documentation contentsA separate mode generates video from a first and a last frame
- Negative promptsNegative prompts list elements that should not appear in the video
3Sora, Google Veo and a third set of camera docs
| Camera point | SceneMixer | Source |
|---|---|---|
| Shot sizes and angles in the docs | Each numbered shot in a segment carries a framing change, written by the storyboard step | SceneMixer, AI storyboard generator page |
| Cuts inside one generation | A segment holds several numbered shots and its length is the sum of them | SceneMixer, AI storyboard generator page |
| A negative prompt | Negative wording is advised against: the guide says to describe what is there, because a named absence tends to be drawn | SceneMixer, say what is there guide |
Inclusion rule. Points where the two models above differ and SceneMixer's guides say something; points its guides leave open are not shown. Order. The order the points take on every model page.