Sign inSign up

skillpilotai/media-mcp

By skillpilotai

•Updated 6 months ago

media-mcp server docker of skill-pilot.ai

Image
0

1.3K

skillpilotai/media-mcp repository overview

⁠Skill Pilot Media Server

An all-in-one Docker image for Skill Pilot AI Agent https://skill-pilot.ai⁠ — image & video generation, talking video, text-to-speech, lip-sync, live avatar, and music creation, ready to run out of the box.

⁠What's Included

ToolDescription
ComfyUIAI image generation, video generation, and talking video via Z-Image and Wan2.2
IndexTTSHigh-quality text-to-speech synthesis
MuseTalkLip-sync video generation and real-time live avatar
SongBloomAI music & song creation

The image is built on runpod/pytorch:2.4.0-py3.11-cuda12.4.1-devel-ubuntu22.04, ensuring compatibility with a wide range of NVIDIA GPUs and CUDA versions.

Tested on NVIDIA RTX 2060 GPU (12 GB VRAM) - MuseTalk live avatar can have real-time performance at 12 FPS.

Supports local GPU acceleration with NVIDIA drivers on the host machine or Runpod Cloud environments.

⁠Quick Start

docker pull skillpilot/media-server:latest
docker run --gpus all \
  -p 18188:8188 -p 17860:7860 -p 18080:8080 \
  -p 13478:3478 -p 13478:3478/udp \
  -p 15349:5349 -p 15349:5349/udp \
  skillpilot/media-server:latest

⁠Exposed Ports

PortProtocolService
22TCPSSH
8188TCPComfyUI
7860TCPUnassigned
8080TCPUnassigned
3478TCP/UDPcoturn STUN/TURN (MuseTalk live avatar)
5349TCP/UDPcoturn STUN/TURN over TLS (MuseTalk live avatar)

⁠Environment Variables

VariableDefaultDescription
PUBLIC_KEY—SSH public key to authorize for the ubuntu user
COTURN_USERskillpilotcoturn TURN server username
COTURN_PASSWORDskillpilot123coturn TURN server password

Set credentials at runtime for security:

docker run --gpus all \
  -e PUBLIC_KEY="your_ssh_public_key" \
  -e COTURN_USER=myuser \
  -e COTURN_PASSWORD=mysecretpassword \
  -p 18188:8188 -p 17860:7860 -p 18080:8080 \
  -p 13478:3478 -p 13478:3478/udp \
  -p 15349:5349 -p 15349:5349/udp \
  skillpilot/media-server:latest

When the container is running, it will automatically download the modeles by comand line below:

huggingface-cli download skill-pilot/media-mcp --local-dir /home/ubuntu/workspace/models

Use command below to check the downloading process in the container:

tmux attach -t download -r

You can use the services until the downloading process is completed. The models will be stored in the /home/ubuntu/workspace/models directory inside the container.

For how to use the media mcp server, please check at https://skill-pilot.ai⁠, and find our Discord server invite link at https://skill-pilot.ai⁠ and join us for support.

⁠Getting Support

We offer free community support — no account required.

  1. Visit https://skill-pilot.ai⁠ to find the Discord invite link.
  2. Join the server and post your question in the relevant channel.
  3. Include your Docker version, GPU info, and any error output for the fastest response.

⁠License

Free and open source https://skill-pilot.ai⁠ · MIT License

All codes included in this image are licensed under their respective licenses. Please refer to the individual codes for details.


Built with love by the Skill Pilot team · https://skill-pilot.ai⁠

Tag summary

Content type

Image

Digest

sha256:d6c328255…

Size

36.7 GB

Last updated

6 months ago

docker pull skillpilotai/media-mcp