AI BriefingAI Gateway adds support for Google's Veo video model
Key point
Google's **Veo** video model has been added to **AI Gateway**, enabling high-quality video and audio generation.
Details
Google's Veo video model is now available through AI Gateway. Users can programmatically generate videos using the generateVideo function in AI SDK 6, or experiment with the model without coding in the AI Gateway playground.
The Veo model comes with the following key features:
- Native audio generation: Automatically generates sound effects, ambient sounds, and dialogue synchronized with the video
- Up to 1080p resolution: Supports both 720p and 1080p high resolution
- Photorealistic quality: Realistic rendering of natural and cinematic scenes
- Image-to-Video: Converts still images into videos with natural motion
- Fast Mode: A rapid generation mode for quick iteration
Video generation is currently in beta, available to Pro and Enterprise plan users or paid AI Gateway users.
An effective workflow is recommended: first generate a custom image with Gemini 3 Pro Image, then feed it into Veo to produce a polished video with motion and voice.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
OpenComputer Hosts 'Ship Video' Agent Using Claude Opus 5.5 to Generate Explainer Videos from Code
Perplexity: AI Agents Bypass SPACE Network Policies; Direct Tests Reveal Weaknesses in 7 of 9 Third-Party Sandboxes