VideoGenReview

What each AI video model's release notes say changed

When did AI video clips reach 30 seconds?

Per generation, the notes read go from 10 seconds with Hailuo 02 in June 2025 to 15 with Wan 2.6 in December, 20 with Sora in March 2026, and 30 with Wan 3.0 on 6 August 2026 and Seedance 2.5, announced on Higgsfield and Luma the same day. Kling's Motion Control reached 30 seconds of action in December 2025. As of 2026-09-25.

The entries by dateOne dot per dated entry.The entries by date2025-04-07Amazon Nova Reel, Nova Reel 1.12025-06-18MiniMax Hailuo, Hailuo 022025-09-23Wan, Wan 2.52025-12-03Wan, Wan 2.62025-12-17Kling AI, Kling 2.62026-03-12Sora, Sora 22026-08-06Seedance, Seedance 2.52026-08-06Seedance, Seedance 2.52026-08-06Wan, Wan 3.02026-08-11Seedance, Seedance 2.52026-08-20Wan, Wan 3.02026-08-24Wan, Wan 3.0
Fig. 1 One dot per dated entry.
Entries that answer this question, oldest first, read 2026-09-25.
DateLineVersionWhat changed
7 April 2025Amazon Nova ReelNova Reel 1.1Multi-shot videos up to two minutes, in an automated mode from one prompt or a manual mode with a prompt per shot
18 June 2025MiniMax HailuoHailuo 02Hailuo 02 generates 1080p and clips of up to 10 seconds
23 September 2025WanWan 2.5Wan 2.5 preview generates synchronised audio and 10 second clips
3 December 2025WanWan 2.6Wan 2.6 text-to-video plans several shots inside one clip of up to 15 seconds
17 December 2025Kling AIKling 2.6Kling 2.6 Motion Control copies an action and expression, up to 30 seconds in one take
12 March 2026SoraSora 2Character references, clips up to 20 seconds, 1080p on Sora 2 Pro, extensions and batch jobs
6 August 2026SeedanceSeedance 2.5Seedance 2.5 arrives on Higgsfield with clips up to 30 seconds
6 August 2026SeedanceSeedance 2.5Seedance 2.5 arrives on Luma with 30-second single-pass generation
6 August 2026WanWan 3.0Wan 3.0 folds reference, editing, replication and driving into one model, with clips up to 30 seconds
11 August 2026SeedanceSeedance 2.5Seedance 2.5 reaches Runway through its MCP, up to 30 seconds
20 August 2026WanWan 3.0Wan 3.0 Prime, a faster version with the same capabilities
24 August 2026WanWan 3.0Wan 3.0 and Wan 3.0 Prime arrive on Higgsfield, up to 30 seconds
Undated version rowSeedanceSeedance 2.5Seedance 2.5: 4 to 30 seconds, 1080p in 10-bit

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

Two different numbers hide behind clip length in release notes. One is how long a single generation can be. The other is how long a clip can grow when it is extended, one generation after another. Runway's Gen-3 Alpha reached 40 seconds in total through extensions as early as September 2024, but each piece was still a short generation. This page follows the first number.

The steps are not evenly spaced. Ten seconds held through most of 2025; fifteen arrived with Wan 2.6's multi-shot planning at the end of the year; Sora's API went to twenty in March 2026. Thirty arrived twice in one day in August 2026, once in Alibaba Cloud's list for Wan 3.0 and once in platform posts for Seedance 2.5, whose own model list gives 4 to 30 seconds.

Kling's December 2025 Motion Control note is a different kind of thirty seconds: an action copied from a reference video in one take, not a clip generated from a prompt.

Amazon's Nova Reel 1.1 is a third kind. From April 2025 one request can return up to two minutes, but as 6-second shots joined together, so each piece is still a 6-second generation.

1In the makers' words

Amazon Nova Reel, 7 April 2025

This update lets you generate multi-shot videos up to 2-minutes in length with consistent style across shots.

AWS News Blog, Amazon Nova Reel 1.1
  • April 7
    Multi-shot videos up to two minutes, in an automated mode from one prompt or a manual mode with a prompt per shot2025AWS News Blog, Amazon Nova Reel 1.1 / since 2025-04-07 / checked 2026-09-25

MiniMax Hailuo, 18 June 2025

Released MiniMax Hailuo 02, a next-generation video generation model with support for 1080p resolution and video generation of up to 10 seconds.

MiniMax, model release notes
  • MiniMax-Hailuo-02
    Hailuo 02 generates 1080p and clips of up to 10 secondsMiniMax, model release notes / since 2025-06-18 / checked 2026-09-25

Wan, 23 September 2025

newly upgraded model architecture supports synchronized audio generation with visuals, enables 10-second long video generation

Alibaba Cloud Model Studio, newly released models

Wan, 3 December 2025

Intelligent shot scheduling supports multi-shot storytelling, generating multi-shot narrative videos with consistent subjects, scenes, and atmosphere, with a maximum duration of 15 seconds.

Alibaba Cloud Model Studio, newly released models

Kling AI, 17 December 2025

30 seconds of high-difficulty action in one seamless take, with total command over movement, expressions, lip-sync, and gestures.

Kling AI, release notes
  • 2025-12-17
    Kling 2.6 Motion Control copies an action and expression, up to 30 seconds in one takeKling AI, release notes / since 2025-12-17 / checked 2026-09-25

Sora, 12 March 2026

Expanded the Sora API with reusable character references, longer generations up to 20 seconds, 1080p output for sora-2-pro , video extensions, and Batch API support for POST /v1/videos .

OpenAI, API changelog
  • March 12
    Character references, clips up to 20 seconds, 1080p on Sora 2 Pro, extensions and batch jobs2026OpenAI, API changelog / since 2026-03-12 / checked 2026-09-25

Seedance, 6 August 2026

Seedance 2.5 from ByteDance is available on Higgsfield, the latest version in the Seedance video family.

Higgsfield, changelog
  • Seedance 2.5
    Seedance 2.5 arrives on Higgsfield with clips up to 30 secondsHiggsfield, changelog / since 2026-08-06 / checked 2026-09-25

Seedance, 6 August 2026

With Seedance 2.5 on Luma you can get native 30-second generation in a single pass

Luma, Seedance 2.5 on Luma post
  • Seedance 2.5: Now Live in Luma
    Seedance 2.5 arrives on Luma with 30-second single-pass generationLuma, Seedance 2.5 on Luma post / since 2026-08-06 / checked 2026-09-25

Wan, 6 August 2026

It supports four-modal all-reference input, up to 30 seconds of video generation, and can parse files, web pages, and complex images.

Alibaba Cloud Model Studio, newly released models

Seedance, 11 August 2026

Generate up to 30 seconds of video with native audio

Runway, changelog
  • Seedance 2.5
    Seedance 2.5 reaches Runway through its MCP, up to 30 secondsRunway, changelog / since 2026-08-11 / checked 2026-09-25

Wan, 20 August 2026

Wan3.0-Video-Prime is the high-speed version of the Wan3.0 video generation model, with capabilities aligned with the Wan3.0-Video standard version.

Alibaba Cloud Model Studio, newly released models

Wan, 24 August 2026

Up to 30 seconds per generation, at 480p, 720p, or 1080p.

Higgsfield, changelog
  • Wan 3.0 and Wan 3.0 Prime
    Wan 3.0 and Wan 3.0 Prime arrive on Higgsfield, up to 30 secondsHiggsfield, changelog / since 2026-08-24 / checked 2026-09-25

Seedance, Undated version row

Duration: 4–30 s

BytePlus ModelArk, model list

Clip length and extension · Which AI video models let you set how much moves? · Which AI video models generate sound with the picture?

2Notes read