🎬

External Model - Video Generation - Veo 3.1

🛠

Cinematic Text-to-Video with Synced Audio via Google's Veo 3.1

Generate cinematic video clips — with synchronized audio — from natural-language direction inside a CNAPS Studio flow. Choose veo-3.1 for top quality or veo-3.1-fast for iterative workflows and social content. Runs on Google's servers via API.

🔑 Requires a Google API key

What it does

This node connects your CNAPS Studio flows to Google's Veo 3.1 video generation models through the Gemini API. Describe your clip in natural language — subject, camera angles, lighting, mood, and audio cues — and the node returns a generated video at your chosen resolution and duration. Because generation runs on Google's servers, you get top-tier generative quality without hosting any model locally.

Problem it solves

  • Cinematic video with audio, no infrastructure — Veo 3.1 generates video with synced audio on Google's hosted infrastructure; nothing to provision locally.
  • Iteration speed — veo-3.1-fast is tuned for quick turnaround, making it practical for iterative prompting and social-format content before committing to a final veo-3.1 render.
  • Finer output control — Negative prompts let you exclude unwanted elements, and seed values make results reproducible across runs — useful when a flow needs consistent output.
  • Video inside a pipeline — Chain generated clips into downstream CNAPS Studio nodes (upscaling, compare, batch processing).

Configuring the Node

Basic Settings

Model name

Model
Best For
veo-3.1
Cinematic video, synced audio, top quality
veo-3.1-fast
Fast video, iterative workflows, social content

System prompt or instruction for video generation

  • Your main instruction for what to generate. Supports natural language including cinematic direction, camera angles, lighting, mood, audio cues, and style references.

Aspect ratio of the generated video

  • 16:9, 9:16

Video-specific settings

  • Output video resolution: 720p, 1080p, 4K
  • Clip durations in seconds: 4, 6, 8

Advanced Options

  • Negative prompt — exclude unwanted elements from the video
  • Seed value — for reproducible results

How Veo 3.1 compares

Veo 3.1 is one of two external video generation options in CNAPS Studio:

Veo 3.1
Sora 2
Provider
Google
OpenAI
Best for
Cinematic video with synced audio; fast iteration via veo-3.1-fast
Fast everyday creation (sora-2), cinematic production (sora-2-pro)
Clip durations
4 / 6 / 8 s
4 / 8 / 12 s
Output resolution control
720p / 1080p / 4K
— (aspect-ratio presets)
Negative prompt
✅
❌
Seed control
✅
❌

Both run inside CNAPS Studio — compare outputs side-by-side with the Video Compare tool, or chain them into a larger pipeline.

Compliance & Provenance

Provider
Google
Provider type
GPAI — General-Purpose AI (GPAI)
License
Google Cloud Terms
EU AI Act risk class
Limited Risk
Art. 50 transparency
Required — outputs are marked. See AI Policy §2.
Region availability
Available globally
Training data summary
Provider model card / training data

For more on how we classify models and mark outputs, see our AI Policy.

Run it now