dottie-talk
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
dottie-talk
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 |
|
|
Command | What |
| HTTP |
| MCP stdio |
| TTS only ( |
| TTS → |
| STT → text on stdout |
| STT with per-word times → SRT captions or |
| same as |
| STT/TTS readiness JSON |
| show or set speech speed (also in the menubar) |
| enable talk-keys-style hotkeys (off by default) |
| disable hotkeys |
| enabled / armed / chords |
| Omarchy menubar icon (hidden until |
| stop the HTTP server |
npx speak "hello" -o hello.wav
speak "hello" -o hello.wav # after dottie-talk bar on (~/.local/bin/speak)
npx transcribe hello.wavNode ≥22. Override STT with DOTTIE_STT=voxtype or DOTTIE_STT=parakeet.
Linux: if voxtype is already on PATH, talk uses it, and downloads base.en on first start when that voxtype has no model yet. If not, on x86_64 first start downloads the AVX2 binary into ~/.cache/dottie-talk/bin and base.en (no sudo, no pacman); on ARM install voxtype yourself. npm start skips the Darwin bin/koko and downloads the linux-bins ELF the same way. Streaming/multipart STT needs parakeet — buffered JSON /v1/audio/transcriptions works on both.
MCP
npm run mcp (stdio). Audio stays on disk or goes to the speakers, so agent context never fills with base64.
Tool | Args | Returns |
|
| text |
|
| streams PCM to the speakers; starts in ~20 ms, not after the whole clip |
|
| saves the file; |
|
| base64 too (old behavior, for apps) |
Streaming needs a player that reads stdin: pw-cat, pacat, aplay, or ffplay. The first one on PATH wins (pw-cat runs with --raw).
Add to Claude Code:
claude mcp add dottie-talk -s user -- node ~/Projects/dottie-talk/mcp.jsRelated MCP server: STT2TTS MCP
Talk-back (Claude Code)
Read Claude's replies aloud through koko. talk-back.js runs as two Claude Code hooks, and skills/ has the /talk and /talk-toggle skills.
Command | What |
| speak this session's last reply, one time |
| talk-back mode: read every reply aloud |
| same as |
| stop playback |
| on or off |
Stop it: type anything (the next prompt cuts playback off), /talk stop, or /talk off. On Linux (Hyprland), Escape stops it too.
What is read: only the final reply. Never thinking, tool calls, or notes written between tool calls. Code blocks, tables, URLs, and markdown marks are dropped.
State: ~/.config/dottie-talk/talk-back/. The saved last reply is per session (last-<session>.txt), so two windows never read each other's reply. The on/off mode is global.
Setup
Start dottie-talk (
npm start), so koko answers on:1314Link the skills:
ln -s ~/Projects/dottie-talk/skills/talk ~/.claude/skills/talk ln -s ~/Projects/dottie-talk/skills/talk-toggle ~/.claude/skills/talk-toggleAdd the hooks to
~/.claude/settings.json:{ "hooks": { "Stop": [{ "hooks": [{ "type": "command", "command": "node ~/Projects/dottie-talk/talk-back.js hook", "timeout": 5 }] }], "UserPromptSubmit": [{ "hooks": [{ "type": "command", "command": "node ~/Projects/dottie-talk/talk-back.js interrupt", "timeout": 5 }] }] } }Restart Claude Code, then
/talk on
The Stop hook saves every reply and speaks it only when the mode is on. It returns at once; playback runs in a detached child. The interrupt hook prints nothing, because UserPromptSubmit output goes into the model's context.
Keys (Linux)
One voice at a time: a new speak (MCP, talk-back, Alt+S) cuts off the one playing, and an older speak that finishes generating after a newer one is dropped.
Talk-keys analog. Off by default. Enable, then keep npm start running so binds arm:
dottie-talk keys on
npm startChord | Action | Omarchy |
Alt+S | Speak selection if present, else clipboard. Second tap stops. | Steals app Alt+S menu accelerators while armed |
Alt+D | Hold to dictate (voxtype push-to-talk) | Steals browser Alt+D address bar while armed; leaves Super+Ctrl+X / F9 alone |
Escape | Stop speak (also cancels one still generating) | Always bound, even with keys off or the server down. Only consumed while a speak is playing or generating |
Config: ~/.config/dottie-talk/config.json
{
"keys": {
"enabled": false,
"speak": "ALT + S",
"stop": "ESCAPE",
"dictate": "ALT + D",
"voice": ""
}
}DOTTIE_TALK_KEYS=on / off overrides enabled. Hotkeys no-op when the HTTP server is down. macOS: use talk-keys.
Bar (Omarchy)
Menubar icon only while npm start is running. Click: keys toggle, speak selection, stop, quit. Middle-click quits.
dottie-talk bar on
dottie-talk startstart on Linux also installs the plugin (sd.dottie-talk) next to Dottie if the bar does not already have it.
Related
talk-keys — macOS hotkeys for speak / dictate
dottie-desktop — desktop app
local-ai-cli — local AI CLI
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for Speech-to-Text
Hosted text-to-speech MCP server: 66 voices in 9 languages, long-form narration, podcasts.
MCP server exposing the AceDataCloud Fish Audio API (text-to-speech with voice conditioning)
MCP server for Text-to-Speech
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceA local voice interface providing high-performance speech recognition and natural text-to-speech with voice cloning capabilities. It enables AI assistants to speak, listen, and engage in character-based voice conversations through integrated MCP tools.-
- AlicenseNot gradedqualityDmaintenanceLocal-first speech-to-text and text-to-speech MCP server. Hot-swappable engines via config.yaml — no code changes, no API keys required.2MIT
- AlicenseNot gradedqualityAmaintenanceLocal voice toolkit over MCP: transcribe audio to text in 25 languages, synthesize speech in 9, and list available voices and languages. Runs fully on-device — no API keys, no cloud.89 npm81MIT
- AlicenseNot gradedqualityCmaintenanceEnables voice-first interactions with AI agents and MCP tools, supporting speech input/output, STT/TTS, and a provider-independent agent core.1MIT