VideoGenReview

What each AI video model's release notes say changed

Q4 2025 in AI video release notes

Q4 2025: 29 dated entries from 11 lines, 6 October 2025 to 23 December 2025. The table lists each; the chart counts them by kind of change. As of 2026-09-25.

Kling writes the most notes this quarter, nine of them, from 2.5 Turbo in October to 2.6 with a sound switch and the Omni video model in December. Sora reached the OpenAI API in October, LTX opened its API at the end of the month, and Veo 3.1 brought extension, reference images and first-and-last frames. Wan 2.6 planned several shots in one clip, Hailuo 2.3 and PixVerse V5.5 were released, Firefly took camera motion from a reference video, and Runway closed the year with Gen-4.5.

Q4 2025 entries by kindCounted from the table. One note can count under several kinds.Q4 2025 entries by kindNew models and snapshots1010Clip length and extension66Sound, voice and lip-sync66References and consistency88Start, end and middle frames55Editing video that exists33Camera and several shots22Motion and performance44Faster and lighter tiers33API, plans and availability44
Fig. 1 Counted from the table. One note can count under several kinds.
Entries in Q4 2025 by kind of change.
Kind of changeEntries
New models and snapshots10
Clip length and extension6
Sound, voice and lip-sync6
References and consistency8
Start, end and middle frames5
Editing video that exists3
Camera and several shots2
Motion and performance4
Faster and lighter tiers3
API, plans and availability4

Inclusion rule. Kinds with at least one entry this quarter; one entry can count under several. Order. The order kinds take on every page.

1Every entry

Every dated entry in Q4 2025, oldest first.
DateLineVersionWhat changed
6 October 2025SoraSora 2The API gains a videos endpoint for Sora 2 and Sora 2 Pro
15 October 2025Google VeoVeo 3.1Veo 3.1 preview adds extension, up to three reference images and first-and-last-frame input
20 October 2025Kling AIKling 2.5 TurboKling 2.5 Turbo for text-to-video and image-to-video, pro mode
21 October 2025ViduVidu Q2Q2 gains reference-to-video, text-to-video and extension
28 October 2025MiniMax HailuoHailuo 2.3Hailuo 2.3 and a 2.3 Fast tier, with body movement, faces and physics named as the gains
29 October 2025LTXNot named in the noteThe LTX API opens with text-to-video and image-to-video
9 November 2025PixVerseNot named in the noteMulti-transition and Swap generation are released
10 November 2025WanWan 2.2Wan 2.2 Animate moves a character photo with the performance from a reference video
11 November 2025Kling AIKling 2.5 TurboKling 2.5 Turbo gains the standard mode
13 November 2025ViduNot named in the noteAudio and video in one output for reference-to-video and image-to-video
17 November 2025Kling AIKling 2.5 TurboKling 2.5 Turbo pro mode takes first and last frames
17 November 2025Google VeoVeo 3.1Veo 3.1 and Veo 3.1 Fast become generally available on Vertex AI
25 November 2025LTXNot named in the noteRetake edits a chosen section of a video from a prompt
2 December 2025PixVersePixVerse V5.5V5.5 is released
3 December 2025WanWan 2.6Wan 2.6 text-to-video plans several shots inside one clip of up to 15 seconds
3 December 2025WanWan 2.6Wan 2.6 image-to-video handles dialogue between several speakers
4 December 2025Kling AIKling AvatarAvatar videos can run five minutes
8 December 2025Google VeoVeo 3.1Veo 3.1 video extension reaches Vertex AI in preview
9 December 2025LTXNot named in the noteAudio-to-video drives a clip from an audio track
11 December 2025RunwayGen-4.5Gen-4.5 is released for all paid plans
15 December 2025Kling AIKling 2.6Kling 2.6 launches with a switch for generating sound
15 December 2025Kling AIKling OmniThe Omni video model launches on a new API driven by prompt words
16 December 2025Adobe Firefly VideoFirefly Video ModelA start frame can be paired with a reference video whose camera motion the generation recreates
16 December 2025Kling AIKling 2.6Kling 2.6 can speak with a chosen voice
16 December 2025WanWan 2.6Wan 2.6 reference-to-video keeps a person's look and voice, with several characters at once
17 December 2025Kling AIKling 2.6Kling 2.6 Motion Control copies an action and expression, up to 30 seconds in one take
18 December 2025Luma RayRay3Ray3 Modify adds keyframe and character reference controls
22 December 2025Kling AINot named in the noteMotion Control in the API takes a reference image and a reference video together
23 December 2025LTXNot named in the noteThe developer console opens to self-service sign-up

Inclusion rule. Entries whose note is dated in this quarter; undated version rows are not in any quarter. Order. By date, oldest first.

2Lines with entries

3Neighbouring quarters