od FAL AI (Kling)
Kling 3.0 Pro Text-to-Video (FAL)
Kling V3 Pro — cinematic text-to-video with multi-shot and native audio (3-15s, 1080p)
fal-kling-v3-t2vGenerate video with this model.
/api/v1/videos/generationsGET /api/v1/videos/generations{
"model": "fal-kling-v3-t2v",
"prompt": "A cinematic drone shot over a coastal city at sunset",
"duration": 5,
"resolution": "720p"
}curl -X POST https://kunya.ai/api/v1/videos/generations \
-H "Authorization: Bearer kunya_YOUR_API_KEY" \
-H "Content-Type: application/json"
-d '{"model":"fal-kling-v3-t2v","prompt":"A cinematic drone shot over a coastal city at sunset","duration":5,"resolution":"720p"}'FAL AI (Happy Horse)
Alibaba Happy Horse 1.1 — reference-driven video (1–9 images), native audio, 1080p
Dokumentacja APIFAL AI (Seedance)
ByteDance Seedance 2.0 Fast via FAL — fast multimodal reference, up to 9 images + 3 videos + 3 audio
Dokumentacja APIKunya
Intelligently routed video generation — Kling for quality, Seedance for speed, resolution-aware selection.
Dokumentacja APIKunya (Kling)
Kling V3 — standard text-to-video with multi-shot and sound effects (5s or 10s)
Dokumentacja API