VideoGenReview

What each AI video model's release notes say changed

When did lip-sync arrive in AI video models?

Kling added lip-sync in December 2024, stretched it to 60 seconds in June 2025 and to several faces in September. PixVerse added lip-sync in July 2025 and text-to-speech lip-sync in September; Vidu's lip-sync from text or audio came in July 2025. PixVerse added voice cloning for lip-sync in July 2026. As of 2026-09-25.

The entries by dateOne dot per dated entry.The entries by date2024-12-23Kling AI, Not named in the note2025-06-30Kling AI, Not named in the note2025-07-14PixVerse, Not named in the note2025-07-28Vidu, Not named in the note2025-09-11PixVerse, Not named in the note2025-09-15Kling AI, Not named in the note2026-07-22PixVerse, Not named in the note
Fig. 1 One dot per dated entry.
Entries that answer this question, oldest first, read 2026-09-25.
DateLineVersionWhat changed
23 December 2024Kling AINot named in the noteLip-sync for videos made with the 1.0 and 1.5 models
30 June 2025Kling AINot named in the noteLip-sync videos can run 60 seconds instead of 10
14 July 2025PixVerseNot named in the noteLip-sync and extend arrive
28 July 2025ViduNot named in the noteLip-sync from text or audio
11 September 2025PixVerseNot named in the noteSound effects and text-to-speech lip-sync inside generation calls
15 September 2025Kling AINot named in the noteLip-sync handles several people on screen and a set start time
22 July 2026PixVerseNot named in the noteVoice cloning for image avatar and lip-sync

Inclusion rule. Entries whose note bears directly on the question. Order. By date, oldest first; undated rows last.

Lip-sync is the older way to make a character speak: take a video and a voice track and move the mouth to match. It came before generated sound in the notes, and it kept developing after generated sound arrived, because it works on footage that already exists.

Kling's notes show the limits loosening. In December 2024 lip-sync worked on videos from its 1.0 and 1.5 models if the face met requirements; by June 2025 the maximum went from 10 to 60 seconds; by September it handled several people on screen and a set start time.

Sound generated with the picture, as in Veo 3 or Kling 2.6, is on its own question page.

1In the makers' words

Kling AI, 23 December 2024

Videos generated by the Video V1.0 model and Video V1.5 model support lip-sync as long as the video meets the facial requirements

Kling AI, API updates
  • 12/23/2024
    Lip-sync for videos made with the 1.0 and 1.5 modelsKling AI, API updates / since 2024-12-23 / checked 2026-09-25

Kling AI, 30 June 2025

Supports increasing the maximum video duration from 10 seconds to 60 seconds

Kling AI, API updates
  • 06/30/2025
    Lip-sync videos can run 60 seconds instead of 10Kling AI, API updates / since 2025-06-30 / checked 2026-09-25

PixVerse, 14 July 2025

Lip-sync, Extend feature release

PixVerse, API changelogs

Vidu, 28 July 2025

Input text/audio to precisely match lip movements in video

Vidu, API update notice

PixVerse, 11 September 2025

Transition function supports `sound_effect` & `lip_sync_tts`

PixVerse, API changelogs
  • 2025/09/11
    Sound effects and text-to-speech lip-sync inside generation callsPixVerse, API changelogs / since 2025-09-11 / checked 2026-09-25

Kling AI, 15 September 2025

Support multi person screen lip-sync and start lip-sync time

Kling AI, API updates
  • 09/15/2025
    Lip-sync handles several people on screen and a set start timeKling AI, API updates / since 2025-09-15 / checked 2026-09-25

PixVerse, 22 July 2026

Voice Cloning Is Now Available for Image Avatar and Lip Sync Generation!

PixVerse, API changelogs

Sound, voice and lip-sync · When did AI video models open to developers? · When did AI video models reach 1080p?

2Notes read