skills.rest
drakulavichdrakulavichCommunity·8 Agent Skills Included

kesha-voice-kit

Offline speech transcription, synthesis, and language detection

Transcribes voice messages and audio files in 25 languages, synthesizes speech in 9 languages, and detects spoken and written language entirely offline. Eliminates cloud APIs, per-minute billing, and privacy risks by running everything locally on Apple Silicon, Linux, and Windows. Exposes every capability through a simple CLI and MCP server so agents and scripts can transcribe, speak, and route by language automatically.
68|7
↗
npx skills add drakulavich/kesha-voice-kit --all -g -y
Available:

Gives the coding agent the project's binding rules for building, testing, and releasing the voice toolkit, including Bun-only runtime, explicit model installs, and worktree-based editing.

All Skills in This Repository (8)

Pure Emerald Level Indicators
📦 In Repo
drakulavichdrakulavich

kesha-voice-kit

Transcribe, synthesize, and detect language locally with a Bun/TS CLI.

Community
Advanced
📦 In Repo
drakulavichdrakulavich

openspec-apply-change

Automate OpenSpec change application with iterative task execution and guardrails.

Community
Advanced
📦 In Repo
drakulavichdrakulavich

openspec-explore

Guide analysis of ideas and requirements through questioning and ASCII diagrams.

Community
Advanced
📦 In Repo
drakulavichdrakulavich

openspec-archive-change

Archive completed OpenSpec changes after validating artifact status and delta specs.

Community
Advanced
📦 In Repo
drakulavichdrakulavich

release-engine

Automate kesha-engine releases with pre-flight audits, version bumps, tags, release notes, smoke tests, and npm publish.

Community
Advanced
📦 In Repo
drakulavichdrakulavich

openspec-propose

Generate proposal.md, design.md, and tasks.md from a user description.

Community
Advanced
📦 In Repo
drakulavichdrakulavich

verify-pin-bump

Verify SHA-256 pin mismatches and update rust/src/models.rs after checks.

Community
Advanced
📦 In Repo
drakulavichdrakulavich

openspec-sync-specs

Merge delta spec changes into main specs while preserving unrelated content.

Community
Advanced

Frequently Asked Questions

FAQPage Schema
How to install Kesha Voice Kit?▼

Run `npx skills add drakulavich/kesha-voice-kit --all -g -y` in your terminal to install all skills in this suite globally.

How to transcribe voice messages offline?▼

Run `kesha --json voice.ogg` after installing; it returns the transcript plus detected language with confidence scores, with no cloud calls.

Can Kesha generate voice notes for Telegram?▼

Yes. `kesha say --format ogg-opus --out reply.ogg "text"` produces messenger-native OGG/Opus voice notes directly, with no ffmpeg needed.

Does Kesha work with Claude Code and other agents?▼

Yes. It ships an MCP server (`kesha mcp`) exposing transcribe, synthesize, and language tools to Claude Code, Cursor, Codex, and OpenClaw.

Does Kesha send my audio to the cloud?▼

No. All speech-to-text, text-to-speech, and language detection run locally after a one-time model download, so voice data never leaves your machine.

Related Repositories in Software Engineering

View All in Software Engineering→
openclawopenclaw
388.4k

openclaw

Run a personal AI assistant across your devices and chat apps

Official📦 120 Skills
obraobra
280.0k

superpowers

Gives coding agents a disciplined workflow from idea to merged code

Community📦 15 Skills
facebookfacebook
248.4k

react

AI agent skills for building, testing, and porting React core

Official📦 14 Skills