Integration

Vidu integration

Vidu (ShengShu Technology) AI video generation. Generates videos from text prompts (text_to_video) or animates a still image (image_to_video), with optional native audio, background music, and movement-amplitude control. Q3 models reach up to 16 seconds and 1080p. Generation is asynchronous: submit a task, then poll get_generation with the task_id until state='success' and read the signed video url from creations[0].url (valid 24 hours; copy to durable storage with a Download File node if you need to keep it).

Connect Vidu How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Vidu.Built from the 3 Vidu tools below, on the connection you add once.

Common Vidu use cases

Animate a product photo into a marketing clip
Poll until state='success' to fetch the MP4 URL
Generate a realistic or anime clip from a text prompt
Detect failures and surface err_code
Bring a generated or retouched image to life
Produce vertical 9:16 clips for social media
Fetch the cover image for a thumbnail
Generate clips with native audio on Q3 models
Create motion from a workflow screenshot or illustration
Batch low-cost generations with off_peak mode

What you can do with Vidu

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Video, 2 operations

image_to_videoImage to videoPOSTAnimate a still image into a video with Vidu (image-to-video). Returns a task_id; poll get_generation until state='success'.
text_to_videoText to videoPOSTSubmit a Vidu text-to-video generation task. Returns a task_id immediately; poll get_generation until state='success'.

Video task, 1 operation

get_generationGet generationGETPoll a Vidu generation task and retrieve the signed video URL once state='success'.

Use Vidu from Claude Code, Cursor or Codex

Connect Vidu in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Vidu operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Vidu

Create your workspace
Sign up free. Nothing to install.
Connect Vidu once
Add your Vidu connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Vidu integration FAQ

What can you do with the Vidu integration?

LiveContext exposes 3 operations on Vidu, covering video and video task. Common uses include Animate a product photo into a marketing clip, Poll until state='success' to fetch the MP4 URL and Generate a realistic or anime clip from a text prompt.