Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@dottie-talk transcribe the file recording.wav"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Local voice: STT + koko TTS (:1314) + HTTP façade (:1320).
Standalone. No gateway. No Dottie.app.
npm install
npm startBins ship in bin/ (macOS). Models download on first boot (~/.cache/parakeet.cpp, ~/.cache/dottie-talk or ~/.dottie).
Platform | STT | TTS |
Apple Silicon (darwin) |
|
|
Omarchy / Linux | system |
|
Command | What |
| HTTP |
| MCP stdio |
| TTS only ( |
| TTS → |
| STT → text on stdout |
| same as |
| STT/TTS readiness JSON |
npx speak "hello" -o hello.wav
npx transcribe hello.wavNode ≥22. Override STT with DOTTIE_STT=voxtype or DOTTIE_STT=parakeet.
Linux: install Voxtype first (Omarchy: Install → AI → Dictation, or voxtype-bin). Streaming/multipart STT needs parakeet — buffered JSON /v1/audio/transcriptions works on both.
talk-keys — macOS hotkeys for speak / dictate
dottie-desktop — desktop app
local-ai-cli — local AI CLI
This server cannot be deployed
MCP server for Speech-to-Text
MCP server exposing the AceDataCloud Fish Audio API (text-to-speech with voice conditioning)
MCP server for Text-to-Speech
AI voice generation: text-to-speech and voice cloning from any MCP client.