Local DSH audio-cover orchestration with external MSST / DDSP dependencies and explicit recording and model-rights boundaries.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-10-30
License
MIT
01What can it help you accomplish?
Run a local AI-cover workflow from DSH
Separation, converted vocals, mixing, technical checks and a separate listening review
DSH users with rights to the source recording and voice weights
02How to install into DeepSeek Harness
Prerequisites
- Node.js >=18, DSH 0.2.1-rc.2 or rc.3, and independently working MSST / DDSP-SVC environments.
- Prepare the MSST package, DDSP 6.2 package and voice models; external projects and weights are not bundled.
- Use recordings and voice weights you have permission to use.
Installation steps
- 01
After preparing materials, run the README installer: `powershell -ExecutionPolicy Bypass -File scripts\install.ps1 -Root D:\AI-Song -Voice 祥子`.
- 02
Restart DSH.
Verify the integration
- Run cover_doctor after installation; missing core dependencies mean the pipeline is not ready end to end.
- Check materials with `node scripts/verify-materials.mjs --root D:\AI-Song --voice 祥子`.
03DSH integration and capability boundaries
Nine local DSH tools coordinate source separation, voice conversion, conditional pitch shifting, mixing and verification.
Local cover pipeline
Source recordings you are authorised to use→Separation, voice conversion, conditional pitch shifting and mixing
Environment setup and technical checks
Local material paths and voice selection→cover_setup discovery and cover_verify technical checks
04Who is it for? When not to use it?
Good for
- DSH users with rights to the source recording and voice weights
Not for
- MSST / DDSP projects and voice weights are not bundled. Configure the external dependencies before running.
- dryRun:true returns commands and expected outputs only. cover_verify performs technical checks; listening review is recorded separately. Commercial quality is not promised.
- MIT covers the plugin code, not external projects, weights, voices, compositions or recordings. Manifests and conversion provenance contain local paths and are intended for local tracing.
05Compatibility, maintenance and safety notes
- MSST / DDSP projects and voice weights are not bundled. Configure the external dependencies before running.
- dryRun:true returns commands and expected outputs only. cover_verify performs technical checks; listening review is recorded separately. Commercial quality is not promised.
- MIT covers the plugin code, not external projects, weights, voices, compositions or recordings. Manifests and conversion provenance contain local paths and are intended for local tracing.
README licenses the plugin code under MIT, with separate rights for external projects and media.
06Frequently asked questions
What must I install before using the DSH cover tools?
Node.js >=18, compatible DSH, working MSST and DDSP-SVC environments, and voice models. The quick start lists an MSST package, DDSP 6.2 and a voice-model package. External projects and weights are not bundled.
Does a dry run prove the cover is valid?
No. dryRun:true returns commands and expected products only. cover_verify performs technical checks, and listening review is recorded separately.
Does the MIT license grant rights to songs or voice models?
No. It covers the plugin code only, not external projects, weights, voices, compositions or recordings. Use materials you are authorised to use.
07Related DSH workflows
weknora
by tencent
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
honcho
by plastic-labs
Memory library for building stateful agents
webnovel-writer
by lingfengqaq
A long-form Chinese web-novel writing assistant for Claude Code and DeepSeek Harness, designed to reduce memory loss and hallucinations in serialized projects of up to 2 million characters.
mirage
by strukto-ai
The World's First Virtual Terminal for AI Agents
08Data and sources
面向 DeepSeek Harness（DSH）的本地 AI 翻唱插件，版本 **1.1.3**。通过 **9 个工具**组织分离、移调、换声、混音和验收。
插件代码采用 MIT，不涵盖外部工程、模型权重、音色、词曲或录音使用权。
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-10-30. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.