Introduction
Veo 3 combines video and audio generation, reducing the need to assemble outputs from separate systems. The unit of generative media becomes a clip with sound rather than only an image or sequence of frames. This brings the technology into closer relation with audiovisual labour and chains of rights.
View full image ↗Preview still from Google DeepMind’s official Veo 3 Chrome city demonstration. Original generated imagery; the source links to the full moving-image example.
Google DeepMind · Rights remain with the respective holders; reproduction does not imply an open licence
Source · Veo 3 demo | Chrome city ↗RESEARCH ACCOUNT
Image and sound emerge as parts of one generated clip.
ANTI-AI ARCHIVE · Revised 2026-10-02
Release and use
Google’s 20 May 2025 introduction distinguishes Veo 3 through audio generation alongside video, within a wider media-tool announcement. Sound need not always be added only after an image sequence is completed, although subsequent editing, voice work and mixing remain possible.
Section sources: Veo 3
Change in creative practice
A clip consequently involves sources and controls for likeness, performance, dialogue and sound. These layers should be documented separately rather than collapsed into a single authorship or rights question because one service outputs them.
Section sources: Veo 3
Sources for this account
Official release scope and demonstration descriptions read; vendor performance claims are not treated as independent test results.
This account expands the archive within the cited scope. Historical interpretation is not presented as the original author’s statement or as a proven causal influence. The account and translation are AI-assisted, pending independent human review. Section references identify evidence without claiming independent verification of every historical statement.
Continue with a comparative question
Compare the methods, forms of control or presentation contexts of this entry and Jukebox: A Generative Model for Music.
Compare the methods, forms of control or presentation contexts of this entry and Veo video generation model.
Compare the methods, forms of control or presentation contexts of this entry and Flow.
Dates & version record
Date displayed for this node: 2025-05 · Historical date recorded for the source: 2025-05
These dates refer to the historical event or recorded version, not this page’s publication date. The original date precision and unresolved questions are retained.
Original sources & further reading
These links lead to the cited paper, article, institution or conference page. External texts retain their source languages.
Veo 3
https://blog.google/innovation-and-ai/products/generative-media-models-io-2025/
URL cited in a research master or supplement; it may have moved or expired
Provenance, translation & verification
Timeline entry #289 · Historical node
Research materials & supplement references · 3
AI Art Genealogy Research Master · p. 34 · 117
Date as recorded: 2025-05
Veo 3 ↗
Veo 3
GenAI Visual Release Chronology Research Master · p. 31 · R167
Date as recorded: 2025-05-20
Veo 3 ↗
Veo 3
GenAI Visual Release Chronology Research Master · p. 31 · R170
Date as recorded: 2025-05
Veo 3 ↗
Google DeepMind — Veo 3
Archive account based on the listed research materials, not a full translation of the linked work. AI-assisted translation; independent human review pending.
The master’s research claims and dates await independent verification.
Cite this node
ANTI-AI ARCHIVE. Veo 3. Art-history node #289. https://salondesrefuses.cn/en/art-history/117
For specific historical claims, also cite the original sources above and include your access date. This account is not a full translation of the linked work.
Adjacent nodes follow chronological order; adjacency does not establish direct influence or causation.