VideoGenReview

What each AI video model's release notes say changed

Preview in AI video release notes

A preview is a release the maker marks as early: available to use, but with the maker keeping room to change it. From 3 source pages, read 2026-09-25; no maker pays to be listed.

Google uses the word most carefully in this register. Veo 3 arrived in the Gemini API as veo-3.0-generate-preview in July 2025 and became generally available in September; Veo 3.1 went through a public preview in October before general availability on Vertex AI in November. Gemini Omni Flash repeated the pattern in 2026.

Alibaba Cloud labels previews in the model name itself, as in wan2.5-t2v-preview. A preview name can be withdrawn once the stable model exists, so a clip made on a preview may not be reproducible later.

The word says nothing about quality. It says how firmly the maker stands behind the model name and its settings for now.

Where the term appearsOne dot per dated entry.Where the term appears2025-07-17Google Veo, Veo 32025-09-23Wan, Wan 2.52025-10-15Google Veo, Veo 3.12025-12-08Google Veo, Veo 3.12026-04-02Google Veo, Veo 3.1 Lite2026-06-30Gemini Omni, Gemini Omni Flash
Fig. 1 One dot per dated entry.
Entries that show the term, 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
23 September 2025WanWan 2.5Wan 2.5 preview generates synchronised audio and 10 second clips
15 October 2025Google VeoVeo 3.1Veo 3.1 preview adds extension, up to three reference images and first-and-last-frame input
8 December 2025Google VeoVeo 3.1Veo 3.1 video extension reaches Vertex AI in preview
2 April 2026Google VeoVeo 3.1 LiteVeo 3.1 Lite reaches Vertex AI in public preview
30 June 2026Gemini OmniGemini Omni FlashGemini Omni Flash preview makes 3 to 10 second clips at 720p and edits them in conversation

Inclusion rule. Entries whose note uses or shows the term. Order. By date, oldest first; undated rows last.

1In the notes

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

Google, Gemini API changelog

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

Alibaba Cloud Model Studio, newly released models

Released Veo 3.1 and 3.1 Fast models in public preview, with new features including: Extending Veo-created videos. Referencing up to three images to generate a video. Providing first and last frame images to generate videos from.

Google, Gemini API changelog

Veo 3.1 supports video extension in Preview.

Google Cloud, Vertex AI release notes

Veo 3.1 Lite is available in public preview .

Google Cloud, Vertex AI release notes

you can generate 3–10 second videos at 720p from text descriptions or animate still images, and then conversationally edit and refine the outputs.

Google, Gemini API changelog

2Using the models, not reading about them

Release notes such as “Preview” matter once a pipeline runs the models; SceneMixer's guides describe how it does:

SceneMixer writes dialogue into the script analysis, assigns each line to a shot with a speaker and a short delivery note, and the video model performs it — picture and audio generated together, so the mouth forms that sentence in the language you chose.

SceneMixer, AI Dialogue Generator (read 2026-10-13)

When you edit a sheet (change the hair, swap the coat, add a scar) or generate a state (the drawn blade, the burnt room), the model starts from the existing image and reads your text as what to change.

SceneMixer, Editing a Sheet or Making a State: Write the Change, Not the Whole Picture (read 2026-10-13)

3Other terms

4Notes read