heygen-com/hyperframes
HyperFrames is an open-source framework that converts HTML, CSS, and media into deterministic MP4 videos, designed for AI agents and automated content creation workflows.
Awesome MCP › Media & Creativity
mberg/kokoro-tts-mcp
Kokoro TTS MCP Server produces spoken audio from text using Kokoro, a compact open-weight text-to-speech model, running locally through ONNX. Setup is a clone plus downloading the model weight files — kokoro-v1.0.onnx and voices-v1.0.bin — into the repository, after which the server runs with uv. Configuration is environment variables covering the voice, speaking speed and language, so output character is set once rather than per call. Generated audio is written as MP3, and optional S3 upload is supported with AWS credentials and region supplied in the same configuration, which turns the server into a small publishing pipeline: an assistant produces narration and it lands in a bucket where something else can serve it. The significant property is that synthesis happens locally with no per-character API billing and no text leaving the machine, which distinguishes it from the hosted text-to-speech servers and matters for volume work or sensitive material. Kokoro is small enough to run on ordinary hardware without a GPU, at some cost in voice quality relative to commercial services. It is a Python project. The audience is people generating narration, audio notes or accessibility audio at volume, who prefer a local model to a metered API.
https://github.com/mberg/kokoro-tts-mcp
Also in Media & Creativity
zcaceres/markdownify-mcp
Markdownify MCP Server is an MCP server that converts various file types and web content into Markdown format, enabling easy content sharing and management within the MCP ecosystem.
samuelgursky/davinci-resolve-mcp
DaVinci Resolve MCP Server is an MCP server that enables AI coding assistants like Cursor and Claude Desktop to control and query DaVinci Resolve through natural language commands.
heshengtao/comfyui_LLM_party
ComfyUI LLM Party is a versatile framework integrating multiple LLMs and MCP server support within ComfyUI to build customizable LLM workflows and AI assistants with social app integration and advanced multi-agent interactions.
MiniMax-AI/MiniMax-MCP
MiniMax-MCP is the official MiniMax Model Context Protocol server enabling MCP clients to interact with advanced AI APIs for text-to-speech, voice cloning, image, and video generation.
elevenlabs/elevenlabs-mcp
The official ElevenLabs MCP server enabling MCP clients to access advanced text-to-speech and audio processing capabilities through ElevenLabs' APIs.
gyoridavid/short-video-maker
Short Video Maker is an open-source tool that automates the creation of short-form videos for social media using the Model Context Protocol and a REST API.
abhiemj/manim-mcp-server
Manim MCP Server is an MCP server that executes Manim animation scripts and returns generated videos, enabling dynamic animation creation through the Model Context Protocol.