Google Adds Veo 3.1 Vids Feature
What happened
Google announced AI upgrades to its Vids product, including free video generation powered by Veo 3.1 from prompts and photos, signaling heavier investment in consumer multimedia AI. The update is part of a broader push to make generative video and image tools more accessible to developers and product teams. (x.com, eweek.com)
Why it matters
Google Vids now lets personal Google accounts create short AI-generated video clips using Google’s Veo 3.1 model and the Lyria 3 audio model, and adds features like directable custom avatars and built-in soundtrack creation. (blog.google) The Vids “Ingredients to Video” workflow can turn up to three photos plus a text prompt into an eight-second clip, and Google is making those video generations available to free users with an account limit reported at ten generations per month; the product also includes one-click publishing to YouTube and on-device-ready soundtrack tools. (workspaceupdates.googleblog.com) (gadgets360.com) Veo 3.1 brings model-level capabilities that matter for output quality: it produces native audio (the model generates synchronized speech and sound instead of requiring a separate audio file), improves consistency across frames so characters and backgrounds stay stable over time, and supports native vertical 9:16 output for mobile-first formats; those capabilities are exposed through Google’s Gemini API, Google AI Studio, and Vertex AI. (blog.google) (ai.google.dev) Google also released Veo 3.1 Lite as a lower-cost/smaller-capacity option aimed at broader developer access, and the Veo 3.1 family (including a “Fast” variant) was initially made available in a paid preview via the Gemini API — a paid preview meaning developers needed a paid API key to access the models for testing. (9to5google.com) (developers.googleblog.com) Within Google’s product stack, the Ingredients to Video path is implemented to preserve subject identity and scene details when synthesizing clips from images, and the model can output higher-resolution results with upscaling to 1080p or 4K for production-quality exports. (workspaceupdates.googleblog.com) (blog.google) The consumer Vids release and the developer-focused Veo 3.1 Lite/paid previews show Google is splitting access by tier: casual creators get limited free clips inside Vids, while programmatic, higher-throughput, or production uses remain available through the Gemini API and Google AI Studio under paid access. (blog.google)
Key numbers
- Google announced AI upgrades to its Vids product, including free video generation powered by Veo 3.1 from prompts and photos, signaling heavier investment in consumer multimedia AI.
- (x.com, eweek.com) Google Vids now lets personal Google accounts create short AI-generated video clips using Google’s Veo 3.1 model and the Lyria 3 audio model, and adds features like directable custom avatars and built-in soundtrack creation.
Quick answers
What happened in Google Adds Veo 3.1 Vids Feature?
Google announced AI upgrades to its Vids product, including free video generation powered by Veo 3.1 from prompts and photos, signaling heavier investment in consumer multimedia AI. The update is part of a broader push to make generative video and image tools more accessible to developers and product teams. (x.com, eweek.com)
Why does Google Adds Veo 3.1 Vids Feature matter?
Google Vids now lets personal Google accounts create short AI-generated video clips using Google’s Veo 3.1 model and the Lyria 3 audio model, and adds features like directable custom avatars and built-in soundtrack creation. (blog.google) The Vids “Ingredients to Video” workflow can turn up to three photos plus a text prompt into an eight-second clip, and Google is making those video generations available to free users with an account limit reported at ten generations per month; the product also includes one-click publishing to YouTube and on-device-ready soundtrack tools. (workspaceupdates.googleblog.com) (gadgets360.com) Veo 3.1 brings model-level capabilities that matter for output quality: it produces native audio (the model generates synchronized speech and sound instead of requiring a separate audio file), improves consistency across frames so characters and backgrounds stay stable over time, and supports native vertical 9:16 output for mobile-first formats; those capabilities are exposed through Google’s Gemini API, Google AI Studio, and Vertex AI. (blog.google) (ai.google.dev) Google also released Veo 3.1 Lite as a lower-cost/smaller-capacity option aimed at broader developer access, and the Veo 3.1 family (including a “Fast” variant) was initially made available in a paid preview via the Gemini API — a paid preview meaning developers needed a paid API key to access the models for testing. (9to5google.com) (developers.googleblog.com) Within Google’s product stack, the Ingredients to Video path is implemented to preserve subject identity and scene details when synthesizing clips from images, and the model can output higher-resolution results with upscaling to 1080p or 4K for production-quality exports. (workspaceupdates.googleblog.com) (blog.google) The consumer Vids release and the developer-focused Veo 3.1 Lite/paid previews show Google is splitting access by tier: casual creators get limited free clips inside Vids, while programmatic, higher-throughput, or production uses remain available through the Gemini API and Google AI Studio under paid access. (blog.google)
