Kling 3.0 Omni

The multimodal Kling video model: one request accepts a prompt, first and last frame, reference images, a feature video and elements, drives voiced characters and lays out shots itself.

производитель модели — Kuaishou; при опорном видео вендор запрещает нативную генерацию звука; до 4K, опорное видео до 15 секунд

Understands

text, images, video

Produces

video, sound effects, speech

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.