Strengths
What it's the best tool for
- 1080p with synced ambient audio
- Extend up to 148 seconds
- Ingredients to Video
- Frame-level insert/remove
- Reference-image support
Limitations
When to reach for something else
- Max 8s per pass before extend
- Price scales with duration
- Strict celebrity/face filters
- Google content filters
Sample output
How Veo 3.1 responds
Prompt
Culinary Reels: chef slicing vegetables in a studio kitchen, light music, knife and oil sounds, 9:16, 8s.
Veo 3.1
Where teams use it
Four scenarios where it pays for itself
01
Cooking Reels
Audio + 1080p
02
Longer stories
Extend to 148s
03
Ingredients to Video
Build scenes modularly
04
Image spots
Frame-accurate edits
About model
More about Veo 3.1
Veo 3.1 Online — Google's AI Video Model
Veo 3.1 shipped on October 14, 2025: native audio, lip-sync, 1080p. Clip lengths 4/6/8s with extend up to 148s. Hosted on NetRoom.
Capabilities
1080p, synced ambient audio, up to 3 reference images, first/last-frame guidance. Ingredients to Video builds scenes from people, objects and backgrounds.
Formats
16:9 and 9:16, extend for longer stories, insert/remove for frame-level edits.
Use Veo 3.1 via the API
The same engine, straight from your code: one key and one balance for text, images, video and sound. Pay only for the requests you make.
curl
curl https://netroom.ai/api/v1/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "google/veo-31", "input": {"prompt": "A cinematic mountain sunrise"}}'The model id is already in the example. The full parameter reference and prices live in GET /api/v1/models and in the docs.
Try Veo 3.1
right now
Free access to basic models. No card, no obligations.