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 June 2025 and text-to-speech lip-sync in September; Vidu's lip-sync from text or audio came in July 2025. From 3 source pages, read 2026-09-25 to 2026-10-25; no maker pays to be listed.
| Date | Line | Version | What changed |
|---|---|---|---|
| 23 December 2024 | Kling AI | Not named in the note | Lip-sync for videos made with the 1.0 and 1.5 models |
| 21 June 2025 | PixVerse | Not named in the note | Camera-control parameters, speech (lip sync) and video extend are released |
| 30 June 2025 | Kling AI | Not named in the note | Lip-sync videos can run 60 seconds instead of 10 |
| 28 July 2025 | Vidu | Not named in the note | Lip-sync from text or audio |
| 11 September 2025 | PixVerse | Not named in the note | Sound effects and text-to-speech lip-sync inside text-to-video, image-to-video and first-and-last-frame calls |
| 15 September 2025 | Kling AI | Not named in the note | Lip-sync handles several people on screen and a set start time |
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
- 12/23/2024Lip-sync for videos made with the 1.0 and 1.5 models
PixVerse, 21 June 2025
Released camera-control parameters, Speech (Lip Sync), and Video Extend.
PixVerse, API changelog
- 2025-06-21Camera-control parameters, speech (lip sync) and video extend are released
Kling AI, 30 June 2025
Supports increasing the maximum video duration from 10 seconds to 60 seconds
Kling AI, API updates
- 06/30/2025Lip-sync videos can run 60 seconds instead of 10
Vidu, 28 July 2025
Input text/audio to precisely match lip movements in video
Vidu, API update notice
- July 28Lip-sync from text or audio2025
PixVerse, 11 September 2025
Added `sound_effect` and `lip_sync_tts` support to Text-to-Video, Image-to-Video, and First and Last Frame Video.
PixVerse, API changelog
- 2025-09-11Sound effects and text-to-speech lip-sync inside text-to-video, image-to-video and first-and-last-frame calls
Kling AI, 15 September 2025
Support multi person screen lip-sync and start lip-sync time
Kling AI, API updates
- 09/15/2025Lip-sync handles several people on screen and a set start time
Sound, voice and lip-sync · When did AI video models open to developers? · When did AI video models reach 1080p?
2Notes read
- Kling AI, API updates, read 2026-09-25
- PixVerse, API changelog, read 2026-09-25
- Vidu, API update notice, read 2026-09-25
3A pipeline on current models
Release notes such as “When did lip-sync arrive in AI video models?” matter once a pipeline runs the models; SceneMixer's guides describe how it does:
Lip sync is the default: the picture stays frame for frame, every line is voiced again and the mouths are moved to match; the original ambience is dropped.
SceneMixer, Lip Sync or Re-perform: Choosing How to Redub a Clip (read 2026-10-13)
Each segment is generated on whatever tier was selected at the time, and the episode composites them together.
SceneMixer, 480P, 720P or 1080P: Which Tier to Pick — “Can I mix tiers in one episode?” (read 2026-10-13)