Skip to main content
V

dsh-ai-voice-cover

vamyane/dsh-ai-voice-cover

AI voice cover for DeepSeek Harness: give any song plus about 10 seconds of reference audio and get a cover sung in that voice — dry vocal and mixed final, with the melody aligned to the original because only timbre is swapped. Supports zero-shot covers and archived voice libraries, automatic semi-tone shift synced with the accompaniment, an isolated Python venv, and runs on GPU or CPU.

Install

dsh plugin --profile web add github:vamyane/dsh-ai-voice-cover

README

dsh-ai-voice-cover

AI voice cover for DeepSeek Harness. One install gives the agent the ai-voice-cover skill: feed it a song plus about 10 seconds of reference audio and it produces a cover sung in that voice.

中文

What it does

Input:

  1. A target song — A the original track with vocals, or B accompaniment + guide vocal
  2. Reference audio (≈10s, any content; or a whole clean recording library for fine-tuning)

Output:

  • Dry vocal output/dry_vocal.wav — the vocal converted to the reference timbre, no accompaniment
  • Final song output/final_song.wav — dry vocal mixed with the accompaniment
  • Manifest output/manifest.json — auto-resolved parameters and engine path

The guarantee: the melody stays aligned with the original — only timbre is swapped; pitch and rhythm come from the source performance.

Capabilities

  • Zero-shot covers from 10 seconds, or archive a clean recording set as a reusable voice
  • Automatic semi-tone shift with accompaniment sync, so a female voice is not sung back as a male one
  • Dual engine with automatic fallback: Seed-VC first, GPT-SoVITS on failure
  • Isolated Python venv (never pollutes system Python), GPU accelerated and CPU capable
  • Pre-delivery self-check: duration, stereo, chroma melody similarity, pitch-range fit, no clipping

Install

dsh plugin --profile desktop add dsh-ai-voice-cover

Refresh the page (or restart DSH) and ai-voice-cover appears in the skill catalog. The plugin market installs it the same way.

Environment

ComponentVersionNotes
DeepSeek Harness>= 0.2.2-rc.1 < 0.3.0-0Uses the ctx.skills registry
Python3.10+The skill creates its own isolated venv
ffmpegrecentBootstrapped on first setup, or use the system one
GPUoptionalCUDA is faster; CPU works with reduced diffusion steps

First setup downloads several GB of model weights (Seed-VC / GPT-SoVITS).

How it is built

  • Skill-bundle plugin: no UI, no /api routes; one bundled skill provider.
  • Never shadows your skills: bundled rank 600, so a same-named skill in a project or ~/.dsh/skills wins.
  • The plugin itself never downloads anything: all downloads happen when the user runs the skill's setup script.
  • Zero runtime dependencies: node built-ins only.

License

MIT for the plugin and the skill's code/docs. Third-party engines and models downloaded at runtime (Seed-VC, GPT-SoVITS, demucs, PyTorch, librosa, …) remain under their own licenses — see NOTICE.md and the skill's DISCLAIMER.md.

Related plugins