midasheng-gen-mcp
llms.txt2 starsChanged 3 months agoApache-2.0View on GitHub
Generate coherent 16 kHz mixed audio scenes - speech, music, sound effects, and ambience in one pass - from structured text captions, powered by MiDashengLM-Gen (Xiaomi Research, LLM-driven autoregressive flow matching). Runs locally on CUDA. Apache-2.0. - MCP tool: audio_scene portmanteau (status, generate, list, get, delete, export, samples, model lifecycle) + midasheng_help + Prefab cards - Structured caption views: caption, asr, speech, sfx, music, env - Backend 11159 (REST + MCP /mcp), webapp 11160 - 9 languages, emotion control, variable-length…
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- llms-full.txtllms.txt
The file
Files
# midasheng-gen-mcp Generate coherent 16 kHz mixed audio scenes - speech, music, sound effects, and ambience in one pass - from structured text captions, powered by MiDashengLM-Gen (Xiaomi Research, LLM-driven autoregressive flow matching). Runs locally on CUDA. Apache-2.0. ## Key links - [README](https://github.com/sandraschi/midasheng-gen-mcp) - [INSTALL](https://github.com/sandraschi/midasheng-gen-mcp/blob/main/INSTALL.md) - [llms-full.txt](llms-full.txt) - full LLM documentation - [arXiv 2608.11804](https://arxiv.org/abs/2608.11804) - [Hugging Face model](https://huggingface.co/mispeech/midashenglm-gen) - [Demo page](https://xingws.github.io/midashenglm-gen-demo/) ## Summary - MCP tool: `audio_scene` portmanteau (status, generate, list, get, delete, export, samples, model lifecycle) + `midasheng_help` + Prefab cards - Structured caption views: caption, asr, speech, sfx, music, env - Backend 11159 (REST + MCP /mcp), webapp 11160 - 9 languages, emotion control, variable-length output via learned stop head
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.