Kesha MCP Server

Connect Kesha to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Give your tools a voice — speech to text and back, 25 languages, up to ~19× faster than Whisper. On your machine. The kesha mcp server is what makes that connection.

What the server does

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.

Installation

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

• Homebrew — brew install drakulavich/tap/kesha-voice-kit · docs/homebrew.md
• OpenClaw — give your LLM agent ears. Install & config: docs/openclaw.md
• Diagnostics — ** kesha doctor, kesha support-bundle (redacted .tar.gz for issues), and kesha logs produce local, content-free diagnostics — see

Worth knowing first

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

Among the monitoring and observability options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Kesha's toolset — Homebrew, OpenClaw, Diagnostics — is a fair guide to whether it matches your workflow. It is maintained by GitHub Actions; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.