Veo 3.1
Veo 3.1 flagship video with true 4K, native audio, dialogue clarity, and extend-video narratives.
Studio is in early access; availability resolves per project after sign-in.
- Endpoints
- 13
- Eligible
- 10
- Input schemas imported
- 13 / 13
- Delivery
- fal.ai
- Weights
- Not stated
- Developer
- Not stated in source
Overview
Veo 3.1, described as Google DeepMind's flagship video model, supports true 4K output with native audio across versatile generation modes. It refines Veo 3's audio foundation with stronger reference adherence, dialogue clarity, and AV sync for longer narratives via extend-video. Output spans 720p, 1080p, and 4K in 16:9 or 9:16 at 24fps. Fast, lite, first-last-frame, and extend endpoints join the base.
Capabilities
- True 4K output
- Native audio generation
- Dialogue clarity plus AV sync
- 720p, 1080p, and 4K multi-ratio
Best for
- Single cinematic shots
- Dialogue scenes
- Multi-shot sequences
Use cases
- Hero-shot generation
- Extended narratives
- Professional 4K delivery
Endpoints
3 under review · 10 eligible. Cataloged is not the same as executable: Studio resolves which endpoints a project can run.
| Endpoint | Task | Catalog status | Inputs |
|---|---|---|---|
fal-ai/veo3.1 | unknown | Under review | 9 fields · requires prompt |
fal-ai/veo3.1/extend-video | video editing | Eligible | 10 fields · requires prompt, video_url |
fal-ai/veo3.1/fast | unknown | Under review | 9 fields · requires prompt |
fal-ai/veo3.1/fast/extend-video | video editing | Eligible | 10 fields · requires prompt, video_url |
fal-ai/veo3.1/fast/first-last-frame-to-video | video editing | Eligible | 11 fields · requires prompt, first_frame_url, last_frame_url |
fal-ai/veo3.1/fast/image-to-video | image to video | Eligible | 10 fields · requires prompt, image_url |
fal-ai/veo3.1/fast/reference-to-video | reference to video | Eligible | 8 fields · requires prompt, image_urls |
fal-ai/veo3.1/first-last-frame-to-video | video editing | Eligible | 11 fields · requires prompt, first_frame_url, last_frame_url |
fal-ai/veo3.1/image-to-video | image to video | Eligible | 10 fields · requires prompt, image_url |
fal-ai/veo3.1/lite | unknown | Under review | 9 fields · requires prompt |
fal-ai/veo3.1/lite/first-last-frame-to-video | video editing | Eligible | 11 fields · requires prompt, first_frame_url, last_frame_url |
fal-ai/veo3.1/lite/image-to-video | image to video | Eligible | 10 fields · requires prompt, image_url |
fal-ai/veo3.1/reference-to-video | reference to video | Eligible | 8 fields · requires prompt, image_urls |
Questions
3.1 versus 3?
Comparable hero shots; 3.1 improves dialogue, sync, extends.
Formats?
720p, 1080p, or 4K in 16:9 or 9:16 at 24fps.