What Kling 2.6 changed, by its release notes
Kling 2.6, in the Kling AI line: 3 entries, 15 December 2025 to 17 December 2025, covering new model, sound, motion and length. Dated before it in this line: Kling Avatar. From 2 source pages, read 2026-09-25; no maker pays to be listed.
| Date | What changed | Kinds | Source |
|---|---|---|---|
| 15 December 2025 | Kling 2.6 launches with a switch for generating sound | new model, sound | Maker's note |
| 16 December 2025 | Kling 2.6 can speak with a chosen voice | sound | Maker's note |
| 17 December 2025 | Kling 2.6 Motion Control copies an action and expression, up to 30 seconds in one take | motion, length | Maker's note |
Inclusion rule. All entries filed under this version: the maker's notes, platform arrivals and undated rows. Order. By date, oldest first; undated rows last.
The entries for Kling 2.6 cluster around a new model or snapshot, sound, voice or lip-sync and motion or performance transfer.
1Each entry
15 December 2025, from Kling AI, API updates
Control whether to include audio when generating videos through the sound parameter.
Kling AI, API updates
- 12/15/2025Kling 2.6 launches with a switch for generating sound
16 December 2025, from Kling AI, API updates
By using prompt and voice_list, a specified voice can be used to generate videos
Kling AI, API updates
- 12/16/2025Kling 2.6 can speak with a chosen voice
17 December 2025, from Kling AI, release notes
30 seconds of high-difficulty action in one seamless take, with total command over movement, expressions, lip-sync, and gestures.
Kling AI, release notes
- 2025-12-17Kling 2.6 Motion Control copies an action and expression, up to 30 seconds in one take
2Versions either side in this line
- Dated before it: Kling Avatar, 1 entry, first dated 4 December 2025.
- Dated after it: Kling Omni, 1 entry, first dated 15 December 2025.
3Same kinds of change elsewhere, within six weeks
- 10 November 2025, Wan: Wan 2.2
- 13 November 2025, Vidu: Not named in the note
- 3 December 2025, Wan: Wan 2.6
- 8 December 2025, Google Veo: Veo 3.1
- 9 December 2025, LTX: Not named in the note
- 16 December 2025, Wan: Wan 2.6
The whole line: Kling AI. Quarter: Q4 2025.
4Notes read
- Kling AI, API updates, read 2026-09-25
- Kling AI, release notes, read 2026-09-25
5Using the models, not reading about them
Release notes such as “Kling 2.6” matter once a pipeline runs the models; SceneMixer's guides describe how it does:
SceneMixer writes dialogue into the script analysis, assigns each line to a shot with a speaker and a short delivery note, and the video model performs it — picture and audio generated together, so the mouth forms that sentence in the language you chose.
SceneMixer, AI Dialogue Generator (read 2026-10-13)
Dubbing replaces the audio of a finished clip; the picture was generated for a different line, so mouth shapes, pauses and shot length all belong to the original language. Native-language generation gives the video model the line in the target language before it renders the shot, so the performance, the pacing and the cut points are built for that language.
SceneMixer, Native-Language Dialogue vs. Dubbing in AI Video (2026): Why the Cast Should Speak the Line (read 2026-10-13)