MCP server generating coherent 16 kHz mixed audio scenes from text - speech, music, sound effects and ambience in one pass - powered by MiDashengLM-Gen (Xiaomi Research). Local-first, runs entirely on your CUDA GPU. Apache-2.0.
4 files for Cursor, GitHub Copilot, Codex, OpenCode and Claude Code: cursorrules, midasheng-gen-mcp copilot-instructions.md, midasheng-gen-mcp AGENTS.md, midasheng-gen-mcp CLAUDE.md — 1,231 tokens loaded in every session.
.github/copilot-instructions.md A 166 tok AGENTS.md A 692 tok CLAUDE.md A 235 tok .cursorrules A 138 tok These files are sandraschi/midasheng-gen-mcp's own configuration — they tell Cursor, GitHub Copilot, Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.