by Kling Direct
Kling O3 Standard via direct API — 720p text-to-video (3-15s)
Detailed content for this model is coming soon.
Kling Direct
Kling V3 native 4K image-to-video via direct API (3-10s)
Kling Direct
Kling V3 Standard via direct API — 720p text-to-video (5/10/15s)
FAL AI (ByteDance)
ByteDance OmniHuman 1.5 — film-grade talking avatar from photo + audio with micro-expressions and cognitive simulation