skills.rest
drakulavich
drakulavichCOMMUNITY
Explore all skills by this author →
𝕏@drakulavichGitHub

kesha-voice-kit

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

68|7|Updated Apr 6, 2026
Search Tags:#offline#voice#transcription#local#tts#languages
One-click install
npx skills add https://github.com/drakulavich/kesha-voice-kit --skill kesha-voice-kit
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: kesha-voice-kit
Source: https://github.com/drakulavich/kesha-voice-kit/tree/main
Command: npx skills add https://github.com/drakulavich/kesha-voice-kit --skill kesha-voice-kit

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Transcribes speech locally, synthesizes speech, and detects language without cloud, preserving privacy.

Core Features & Use Cases

  • Local, offline STT with 25-language support; TTS in 9 languages; language detection.
  • Runs entirely in Bun/TS wrapper around a Rust engine; no API keys or cloud.
  • Use cases include transcribing voice memos, generating speech responses, and building offline agents.

Quick Start

Install Kesha, fetch the engine with kesha install, and transcribe an audio file.

Frequently Asked Questions about kesha-voice-kit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe audio locally without sending data to the cloud?▼

Offline voice transcription is achieved by running a self-contained Bun/TS wrapper around a Rust engine directly on-device. It transcribes audio files locally without requiring API keys or cloud connectivity, preserving data privacy.

Can I generate speech responses offline for multiple languages?▼

Offline text-to-speech synthesis supports generating speech responses in 9 languages. The toolkit runs entirely locally without cloud dependencies, enabling voice synthesis for multi-language applications.

Does local speech-to-text work with language detection across multiple languages?▼

Local speech-to-text supports 25 languages and includes built-in language detection capabilities. The offline toolkit identifies the spoken language and transcribes it without needing any cloud-based detection service.

What do I need to install to start transcribing voice memos locally?▼

Install the Kesha toolkit, fetch the Rust engine via the install command, and run the transcription script on your audio file. The toolkit ships with pinned models and explicit install steps for a self-contained setup.

When should I choose offline voice transcription over cloud-based speech APIs?▼

Choose offline voice transcription when building privacy-focused agents or workflows requiring on-device processing. It is ideal when you must ship a self-contained tool without relying on external cloud API keys or internet connectivity.

Related Skills

Explore More Software Engineering Skills→
svssdevasvssdeva
1

bun-runtime

Migrate JavaScript and TypeScript projects to the Bun runtime and toolchain.

Community
Intermediate
damionrashforddamionrashford
15

media-tts-ai

Synthesize audio from text using open-source TTS models.

Community
Advanced
steipetesteipete
385.7k

openai-whisper

Transcribe local audio files to text or subtitles using the Whisper CLI.

Community
Intermediate
rgbkrkrgbkrk
20

voice

Transcribe speech and synthesize text with Rust and candle.

Community
Advanced