01
Audio Is Generated, Not Added
Dialogue, ambience and effects come out of the same pass as the picture, so they match what is on screen. Every other model here returns a silent clip you then have to score.
popular
Veo 3.1
Veo 3.1 is Google DeepMind's video model, and the only one in this catalog that treats audio as part of the generation rather than something you add afterwards. It also takes reference images for subject consistency, which is what lets it sit inside a reel instead of only producing standalone clips.
示意模型規格參數
模型規格
最高解析度
4k
最長長度
8s
速度
~90s per clip
單次點數價格
2000 credits / 5s clip
能力
支援的功能
運作方式
核心功能
02
Reference Images, Up to Three
Veo 3.1 accepts reference images for consistent subject appearance, which is why it qualifies for the reel pipeline. A model that only reads a start frame cannot hold a face past shot one.
03
4K Output
Up to 4K at 16:9 or 9:16, 4 to 8 seconds. The most expensive model in the catalog and the one to reach for when the shot has to carry the reel.
常見問題
常見問題解答
相關