Kling VIDEO 2.6
Video modelPrevious generationCard summarizedSee the sound, hear the visual
Source: KLING VIDEO 2.6 User Guide (official model guide; no system card published)
Where to call it
- Kling AI API (new API)
POST /text-to-video/kling-2.6, /image-to-video/kling-2.6
Good for
- Talking-to-camera clips: product showcases, vlogs, news-style reports, speeches
- Multi-person dialogue and singing with lip sync
- Ambient and action sound effects matched to the visuals
Overview
Kuaishou · 03Kling, front
Kling 2.6
See the sound, hear the visual
Typical price
$0.14 / sec
1080p, native audio
- Max resolution
- 1080p
- Max length
- 10 s
- Modes
- text-to-video, image-to-video (first frame / first + last frame)
- Released
- 15 Dec 2025
VIDEO 2.6 is Kling's first native-audio model: one generation produces visuals plus voiceover, dialogue, singing, sound effects and ambience. It supports text-to-video and image-to-video, 5 or 10 s, with speech in Chinese and English. Kling 3.0 has since superseded it. User guide §1–2
kling-v2-6- Typical price
- $0.14 / sec
- Max resolution
- 1080p
- Max length
- 10 s
- Aspect ratios
- 16:9, 9:16, 1:1
- Sound
- Generated with the video
- Released
- 15 Dec 2025
- text-to-video
- image-to-video (first frame / first + last frame)
- native audio (speech, dialogue, singing, sound effects, ambience)
- voice control (up to 2 custom or preset voices)
- motion control