VideoGenReview

What each AI video model's release notes say changed

Which AI video models generate sound with the picture?

In the notes read: Veo 3 from its preview in July 2025, the Wan 2.5 preview in September 2025 and later Wan versions, Vidu's joint audio and video output from November 2025, Kling 2.6's sound switch in December 2025 and Grok Imagine 1.5 with preset voices in July 2026. Kling's earlier video-to-audio adds sound afterwards. As of 2026-09-25.

The entries by dateOne dot per dated entry.The entries by date2025-07-17Google Veo, Veo 32025-08-01Kling AI, Not named in the note2025-09-23Wan, Wan 2.52025-11-13Vidu, Not named in the note2025-12-03Wan, Wan 2.62025-12-15Kling AI, Kling 2.62026-07-31Grok Imagine, Grok Imagine 1.52026-08-11Seedance, Seedance 2.52026-08-13Grok Imagine, Grok Imagine 1.52026-08-24Wan, Wan 3.0
Fig. 1 One dot per dated entry.
Entries that answer this question, oldest first, read 2026-09-25.
DateLineVersionWhat changed
17 July 2025Google VeoVeo 3Veo 3 preview arrives in the Gemini API and generates sound with the picture
1 August 2025Kling AINot named in the noteVideo-to-audio adds sound to any Kling video, and text-to-audio arrives
23 September 2025WanWan 2.5Wan 2.5 preview generates synchronised audio and 10 second clips
13 November 2025ViduNot named in the noteAudio and video in one output for reference-to-video and image-to-video
3 December 2025WanWan 2.6Wan 2.6 image-to-video handles dialogue between several speakers
15 December 2025Kling AIKling 2.6Kling 2.6 launches with a switch for generating sound
31 July 2026Grok ImagineGrok Imagine 1.5Grok Imagine video 1.5 adds reference-to-video with preset voices and native 1080p
11 August 2026SeedanceSeedance 2.5Seedance 2.5 reaches Runway through its MCP, up to 30 seconds
13 August 2026Grok ImagineGrok Imagine 1.5Grok Imagine 1.5 reaches Runway's MCP, 1 to 15 seconds with audio
24 August 2026WanWan 3.0Wan 3.0 arrives in Runway at 480p, 720p or 1080p

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

The difference that matters is whether sound is generated in the same pass as the picture or laid onto a finished clip. Kling's August 2025 note is the second kind: video-to-audio works on any Kling video, including one made earlier. Its December 2025 note on Kling 2.6 is the first kind, a switch on the generation itself.

Platform posts repeat the claim for the models they host: Runway describes Seedance 2.5, Grok Imagine 1.5 and Wan 3.0 as generating with native audio or with audio. Those are the platforms' words about someone else's model, so they sit here as arrivals rather than as the maker's own note.

Sound entries that only take audio in, such as LTX's audio-to-video, are not on this page; they are on the audio kind-of-change page.

1In the makers' words

Google Veo, 17 July 2025

Launched veo-3.0-generate-preview , the latest update to Veo introducing video with audio generation.

Google, Gemini API changelog
  • July 17
    Veo 3 preview arrives in the Gemini API and generates sound with the picture2025Google, Gemini API changelog / since 2025-07-17 / checked 2026-09-25

Kling AI, 1 August 2025

Supports adding audio to all videos generated by Kling models

Kling AI, API updates
  • 08/01/2025
    Video-to-audio adds sound to any Kling video, and text-to-audio arrivesKling AI, API updates / since 2025-08-01 / 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

Vidu, 13 November 2025

Audio&video direct output is now available for Vidu Reference to Video and Image to Video.

Vidu, API update notice
  • November 13
    Audio and video in one output for reference-to-video and image-to-video2025Vidu, API update notice / since 2025-11-13 / checked 2026-09-25

Wan, 3 December 2025

supports stable multi‑speaker dialogue with more natural and realistic vocal timbres

Alibaba Cloud Model Studio, newly released models

Kling AI, 15 December 2025

Control whether to include audio when generating videos through the sound parameter.

Kling AI, API updates
  • 12/15/2025
    Kling 2.6 launches with a switch for generating soundKling AI, API updates / since 2025-12-15 / checked 2026-09-25

Grok Imagine, 31 July 2026

grok-imagine-video-1.5 now supports text-to-video, image-to-video, and reference-to-video (including optional preset voices), with native 1080p for T2V and I2V.

xAI, API release notes
  • July 31
    Grok Imagine video 1.5 adds reference-to-video with preset voices and native 1080pxAI, API release notes / since 2026-07-31 / checked 2026-09-25

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

Grok Imagine, 13 August 2026

Generate 1-15 second clips with native audio, up to 1080p resolution.

Runway, changelog
  • Grok Imagine 1.5 Video
    Grok Imagine 1.5 reaches Runway's MCP, 1 to 15 seconds with audioRunway, changelog / since 2026-08-13 / checked 2026-09-25

Wan, 24 August 2026

Wan 3.0 is now available in Runway in tool mode and workflows.

Runway, changelog
  • Wan 3.0
    Wan 3.0 arrives in Runway at 480p, 720p or 1080pRunway, changelog / since 2026-08-24 / checked 2026-09-25

Sound, voice and lip-sync · When did AI video clips reach 30 seconds? · When did AI video models get 4K output?

2Notes read