by drakulavich · Codex Skill · ★ 59
Kesha Voice Kit Give your local tools and LLM agents a voice.Fast speech-to-text, text-to-speech, voice-activity detection, and language detection in one local-first CLI: Apple Silicon CoreML first, ONNX fallback on supported Linux/Windows builds. Transcribe locally — 25 languages, up to 19x faster than Whisper on Apple Silicon, 2.5x on CPU Speak back — text-to-speech in 9 languages Plug into agents — ship voice workflows as CLI commands, an MCP server, an OpenClaw skill, or a <a href
| Stars | 59 |
| Forks | 7 |
| Language | Rust |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 69.1891532444722/100 |
| Open Issues | 9 |
| Last Updated | 2026-07-07 |
| Created | 2026-04-06 |
| Platforms | rust |
| Est. Tokens | ~24k |
These tools work well together with kesha-voice-kit for enhanced workflows:
Explore other popular codex skill tools:
kesha-voice-kit is Give your tools a voice — speech to text and back, 25 languages, up to ~19× faster than Whisper. On your machine.. It is categorized as a Codex Skill with 59 GitHub stars.
kesha-voice-kit is primarily written in Rust. It covers topics such as apple-silicon, asr, bun.
You can find installation instructions and usage details in the kesha-voice-kit GitHub repository at github.com/drakulavich/kesha-voice-kit. The project has 59 stars and 7 forks, indicating an active community.
kesha-voice-kit is released under the MIT license, making it free to use and modify according to the license terms.