Kesha Voice Kit

Registry Snapshot

Repository

https://github.com/drakulavich/kesha-voice-kit

Homepage

https://github.com/drakulavich/kesha-voice-kit

Canonical profile

https://hol.org/registry/plugins/drakulavich%2Fkesha-voice-kit

Publisher verification

No

Marketplace source

Unknown

Scanner

Broker fallback

Safety label

caution

Digest verified

Yes

Marketplace Source

Repo URL

https://github.com/drakulavich/kesha-voice-kit

Marketplace path

Unknown

Source path

.

Install policy

Unspecified

npx skills add drakulavich/kesha-voice-kit

• openspec-apply-change

  .claude/skills/openspec-apply-change/SKILL.md

  Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks. Also use when the user says "openspec apply", "opsx apply", or "openspec implement".

  Raw SKILL.md

  SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

• openspec-archive-change

  .claude/skills/openspec-archive-change/SKILL.md

  Archive a completed OpenSpec change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete. Also use when the user says "openspec archive" or "opsx archive".

  Raw SKILL.md

  SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

• openspec-explore

  .claude/skills/openspec-explore/SKILL.md

  Enter OpenSpec explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements in a project that uses OpenSpec. Use when the user wants to think through something before or during an OpenSpec change. Also use when the user says "openspec explore" or "opsx explore".

  Raw SKILL.md

  SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

• openspec-propose

  .claude/skills/openspec-propose/SKILL.md

  Propose a new OpenSpec change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation. Also use when the user says "openspec propose" or "opsx propose".

  Raw SKILL.md

  SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

• openspec-sync-specs

  .claude/skills/openspec-sync-specs/SKILL.md

  Sync delta specs from an OpenSpec change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change. Also use when the user says "openspec sync" or "opsx sync".

  Raw SKILL.md

  SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

• release

  .claude/skills/release/SKILL.md

  Cuts a Kesha release through release.yml — a stable vX.Y.Z tag, a dispatched beta, or an alpha — and explains the release machinery. One version names the CLI and the Engine. Covers the version bump, the annotated tag, what the run publishes and in what order, how to verify from the registry, re-recording the capability pacts, and recovery. Refuses to auto-run; the maintainer invokes it explicitly.

  Raw SKILL.md

  SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

• tts-internals

  .claude/skills/tts-internals/SKILL.md

  Use when working on kesha TTS internals — voice routing and which engine serves which voice-id prefix, Kokoro/Vosk ONNX I/O shapes, the CharsiuG2P vs FluidAudio G2P split, SSML handling, multilingual behaviour (es/fr/it/pt on ONNX, hi/ja/zh on darwin-arm64), or the KESHA_* TTS environment variables. Explains why darwin-arm64 routes differently from every other build.

  Raw SKILL.md

  SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

• verify-pin-bump

  .claude/skills/verify-pin-bump/SKILL.md

  Use when a model SHA-256 mismatch surfaces (download_verified errors, manifest_tests failures, a fresh download hashing differently from the rust/src/models/manifest.rs pin, kesha install failing after an update, a KESHA_MODEL_MIRROR swap producing a different hash, or an upstream HuggingFace re-upload). Walks through the safe bump procedure — verify the upstream weights deliberately, then update the pin. Refuses to suggest commenting out verification.

  Raw SKILL.md

  SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

• kesha-voice-kit

  SKILL.md

  Local multilingual voice toolkit — speech-to-text (STT), text-to-speech (TTS), speaker diarization, and language detection, over a CLI or an MCP server. Runs entirely offline on Apple Silicon, Linux, and Windows. No API keys, no cloud. NVIDIA Parakeet TDT for STT across 25 European languages, Kokoro-82M + Vosk-TTS for TTS in 9 languages, plus macOS AVSpeechSynthesizer for ~180 system voices with zero install.

  Raw SKILL.md

  SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.