CONFIRMEDDate confidence: CONFIRMEDStated as firmHow firmly the source words the date: confirmed, scheduled, estimated, delayed or unverified.Show all CONFIRMED pins82% CONFIDENCEOverall confidence: 82%How well the pin's source and references back up its dates.Weighted average of how firmly 4 references, the source included, support the pin's start and end times; a reference counts half as much for every 180 days older than the newestShow all pins at 75% confidence or better
ScriptByAI's[4] timeline dates Video 2.6 to 3 December 2025, two days after Video O1; the press release is datelined Beijing, 4 December ("today unveiled"), a time-zone difference.- Start
- Dec 3, 202590% CONFIDENCEfrom the source · possible Dec 3 – 21, 2025
Kling 2.6 Released
Kling AI launches Video 2.6, its first model with native audio: voices, singing, sound effects and ambience generated in one pass with the picture, in English and Chinese, for 5 and 10 second clips.
- Kling AI unveiled Video 2.6 on 3 to 4 December 2025, two days after Video O1, as its first model to generate speech, singing, rapping, sound effects and ambience together with the video in a single step[2][3]
- Creators can set emotion, tone, rhythm and volume for dialogue, and the model aligns speech and ambient sound to on-screen motion; it supports 5 and 10 second clips with English and Chinese voice output[2]
- Voice Control (16 December) lets users train or upload a voice so characters keep the same voice across clips, and Motion Control (17 December) maps 3 to 30 second reference footage onto a character[3]
- Partner platforms sold it for about $0.07 to $0.14 a second[3]; a Decoder-reported academic benchmark of video reasoning placed Kling 2.6 at 0.369, behind Sora 2 (0.546) and Veo 3.1 (0.480)
- It followed the sound-effects add-on of 2.1 and set up the 15-second multilingual audio of Kling 3.0