od FAL AI (ByteDance)
OmniHuman
ByteDance OmniHuman — audio-driven avatar animation with emotion and cognitive simulation
omnihuman-v1Generate video with this model.
/api/v1/videos/generationsGET /api/v1/videos/generations{
"model": "omnihuman-v1",
"prompt": "A cinematic drone shot over a coastal city at sunset",
"duration": 5,
"resolution": "720p",
"image_url": "https://example.com/start-frame.jpg"
}curl -X POST https://kunya.ai/api/v1/videos/generations \
-H "Authorization: Bearer kunya_YOUR_API_KEY" \
-H "Content-Type: application/json"
-d '{"model":"omnihuman-v1","prompt":"A cinematic drone shot over a coastal city at sunset","duration":5,"resolution":"720p","image_url":"https://example.com/start-frame.jpg"}'FAL AI (Happy Horse)
Alibaba Happy Horse 1.1 — natural language video editing with reference images, native audio
Dokumentacja APIFAL AI
Fast face puppeteering - your expressions control any face
Dokumentacja APIGoogle Veo 3.1 — fast cinematic generation (up to 8s, 720p); native audio always on
Dokumentacja APIKling Direct
Kling O3 native 4K text-to-video via direct API (3-15s)
Dokumentacja API