What can you do with the D-ID integration?

LiveContext exposes 29 operations on D-ID, covering agent, animation, clip and knowledge. Common uses include Clean up test clips, Clean up test animations and Remove deprecated agents.

LiveContext

All integrations

D-ID integration

AI-powered video creation platform for generating photorealistic talking avatar videos. Transform images into speaking characters, clone voices, create personalized video content at scale. Ideal for building applications requiring AI presenters, video personalization, and automated video content generation.

29 toolsBasic authAPI docs

Connect D-ID How integrations work

Common D-ID use cases

Clean up test clips
Clean up test animations
Remove deprecated agents
View agent configuration
Poll clip generation status
Remove outdated knowledge bases
Display clip library in dashboard
Display agent management dashboard
Clean up test videos to save storage
Poll knowledge base processing status

What you can do with D-ID

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.

Agent, 5 operations

POSTcreate_agent
Create a new AI visual agent with a presenter avatar, voice, and optional LLM-powered conversation capabilities.
DELETEdelete_agent
Permanently delete an AI agent and its configuration.
GETget_agent
Retrieve the configuration and details of a specific AI agent.
GETlist_agents
Retrieve a list of all AI agents created by the authenticated user.
PATCHupdate_agent
Update an existing AI agent's configuration including presenter, LLM, knowledge base, and other settings.

Animation, 4 operations

POSTcreate_animation
Create a face animation by transferring motion from a driver video to a source image.
DELETEdelete_animation
Permanently delete a face animation and its associated data.
GETget_animation
Check the processing status and retrieve results of a face animation generation task.
GETlist_animations
Retrieve a paginated list of all face animations created by the authenticated user.

Clip, 4 operations

POSTcreate_clip
Create a FULL-HD photorealistic video clip using a pre-made V3 Pro Avatar presenter with text or audio.
DELETEdelete_clip
Permanently delete a video clip and its associated data.
GETget_clip
Retrieve the status and details of a previously created V3 Pro Avatar video clip.
GETlist_clips
Retrieve a paginated list of all video clips created by the authenticated user.

Knowledge, 4 operations

POSTcreate_knowledge
Create a new knowledge base for use with AI agents via RAG (Retrieval-Augmented Generation).
DELETEdelete_knowledge
Permanently delete a knowledge base and all its indexed content.
GETget_knowledge
Retrieve the details and processing status of a specific knowledge base.
GETlist_knowledge
Retrieve a paginated list of all knowledge bases created by the authenticated user.

Talk, 4 operations

POSTcreate_talk
Create a talking avatar video by animating a static image with synchronized speech from text or audio input.
DELETEdelete_talk
Permanently delete a talking avatar video and its associated data from the system.
GETget_talk
Retrieve the status and details of a previously created talking avatar video generation task.
GETlist_talks
Retrieve a paginated list of all talking avatar videos created by the authenticated user.

Presenter, 2 operations

GETget_presenter_drivers
Retrieve all available driver animations for a specific presenter avatar.
GETlist_presenters
Retrieve the catalog of pre-made presenter avatars available for immediate use in clip generation.

Stream, 2 operations

POSTcreate_talk_stream
Initialize a real-time WebRTC streaming session for interactive talking avatar conversations with low latency.
DELETEdelete_talk_stream
Terminate and delete a real-time talk streaming session.

Audio, 1 operation

POSTupload_audio
Upload an audio file to D-ID's temporary storage for use in talk or animation video generation.

Credit, 1 operation

GETget_credits
Retrieve the user's credit balance including remaining and total credits with expiration details.

Image, 1 operation

POSTupload_image
Upload an image file to D-ID's temporary storage for use as an avatar source in video generation.

Voice, 1 operation

GETlist_voices
Retrieve available text-to-speech voices across supported providers for use in video generation.

Use D-ID from Claude Code, Cursor or Codex

Connect D-ID in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its D-ID 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 D-ID

Create your workspace
Sign up free. Nothing to install.
Connect D-ID once
Add your D-ID 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.

D-ID integration FAQ

What can you do with the D-ID integration?: LiveContext exposes 29 operations on D-ID, covering agent, animation, clip and knowledge. Common uses include Clean up test clips, Clean up test animations and Remove deprecated agents.