MCP For Claude Marketplace
D-ID

D-ID MCP Connector for Claude

A+

Create AI videos via D-ID — generate talking avatars from text or audio, list stock presenters, and monitor credit balance directly from any AI agent.

10 tools Official Updated Oct 1, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect your D-ID account to any AI agent and take full control of your AI video generation and digital human workflows through natural conversation.

What you can do

  • Talking Avatar Generation — Create high-quality videos where an AI avatar speaks your text with precise lip-sync and natural expressions using Microsoft or Amazon TTS
  • Audio-to-Video Sync — Provision talking avatars from pre-recorded audio files, allowing the agent to generate videos that match your literal audio boundaries
  • Digital Presenters — List and retrieve available D-ID stock presenters including pre-built digital humans and background options for fast video production
  • Media Uploads — Upload face images to D-ID servers to use them as custom avatar sources for your personalized video content
  • Run Monitoring — Track the status of your talks and clips (created, started, done, error) and retrieve final result URLs when processing is complete
  • Credit Auditing — Get your current D-ID credit balance and plan info to verify remaining limits and manage video generation quotas

How it works

  1. Subscribe to this server
  2. Enter your D-ID API Key (found in D-ID Studio > Account Settings)
  3. Start generating AI videos from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • Content Creators — generate personalized video messages and social media content without manual editing
  • Marketers — create localized talking head videos for different markets using various TTS providers and voices
  • Product Teams — quickly prototype digital human interactions and verify video outputs through natural language
  • Developers — test and debug D-ID video generation pipelines and presenter mappings directly from the chat
talking-avatarsgenerative-ailip-synctext-to-videodigital-humansvideo-production

10 tools expose this connector's capabilities to your AI agent.

create_talk

Create a talking avatar video using D-ID. An AI avatar speaks your text with lip-sync and natural expressions

get_talk

Wait for creation to finish. Get status of a D-ID talk. Returns status (created/started/done/error), result_url when done

list_talks

List all D-ID talks. Returns talk IDs, statuses, and creation timestamps

list_presenters

List available D-ID presenters. Returns presenter IDs, names, and preview images

create_clip

Create a D-ID clip using a stock presenter (no image needed). Pre-built digital humans with backgrounds

create_talk_audio

Create a D-ID talking avatar from a pre-recorded audio file. Avatar lip-syncs to your audio

delete_talk

Delete a D-ID talk

get_clip

Get status of a D-ID clip. Returns status and result URL

get_credits

Get current D-ID credit balance and plan info

upload_image

Upload a face image to D-ID for use as avatar source. Returns image URL

See how to talk to your AI agent using D-ID.

Create a talking avatar video with script: 'Welcome to our new platform!'

Talk generation started! I've used a default presenter and voice to process your script. Talk ID: 'tlk_abc123'. I will monitor the status and let you know when the result URL is ready.

List all available D-ID presenters

I found 15 presenters. Available stock humans include 'Amy' (ID: presenter_1), 'Brian' (ID: presenter_2), and 'Claire' (ID: presenter_3). You can use these IDs to create clips instantly.

How many credits do I have left in D-ID?

You currently have 45 credits remaining on your 'Pro' plan. Based on your settings, this is enough to generate approximately 15 minutes of new AI video content.

Yes. Use the 'create_talk' tool and specify the TTS provider (microsoft or amazon) and the exact voice ID. The agent will orchestrate the request to generate an avatar that speaks your script with that specific vocal identity.

Related Connectors

Synthesia

Synthesia MCP

10 tools Official

Produce professional AI videos with lifelike avatars that present in 140+ languages without cameras, studios, or actors.

A+ View details →
Fliki (AI Text-to-Video & Speech API)

Fliki (AI Text-to-Video & Speech API) MCP

3 tools Official

Create high-quality videos and AI voices from text scripts using Fliki — generate content, list voices, and track rendering status.

A+ View details →
ElevenLabs

ElevenLabs MCP

34 tools Official

Generate lifelike speech, clone voices, and create sound effects using ElevenLabs' industry-leading AI audio technology.

A+ View details →
Play.ht (AI Voice Generation & TTS)

Play.ht (AI Voice Generation & TTS) MCP

3 tools Official

Generate ultra-realistic AI voices and convert text to speech instantly using Play.ht's advanced neural engine.

A+ View details →