Schema | mac-voice-mcp

mac-voice-mcp

Overview Schema Source Related Servers Discussions Admin

Server Configuration

Describes the environment variables required to run the server.

Name	Required	Description	Default
`VOICE_MCP_RATE`	No	Words per minute, e.g. 200.	system rate
`VOICE_MCP_CHIME`	No	Set to 0 to turn off the mic open/close sounds.	1
`VOICE_MCP_DEBUG`	No	Verbose logs with per-turn timings, written to stderr.	0
`VOICE_MCP_VOICE`	No	macOS voice, e.g. Samantha, Daniel, Kanya. List them with `say -v '?'`.	system voice
`VOICE_MCP_THREADS`	No	Number of whisper.cpp threads.	min(8, cores)
`VOICE_MCP_LANGUAGE`	No	en, th, ja, de, …	en for *.en models, otherwise auto
`VOICE_MCP_RECORDER`	No	sox or ffmpeg (ffmpeg is macOS only).	auto
`VOICE_MCP_CACHE_DIR`	No	Where models are downloaded or symlinked.	~/.cache/mac-voice-mcp
`VOICE_MCP_MIN_SPEECH_DB`	No	The quietest level that ever counts as speech (dBFS).	-48
`VOICE_MCP_WHISPER_MODEL`	No	Which model to use (see the table below).	base.en
`VOICE_MCP_END_SILENCE_MS`	No	How long a pause ends your turn. Use 1800 if it cuts you off while you think, 800 for snappier replies.	1200
`VOICE_MCP_WHISPER_PROMPT`	No	Words to bias toward: names, product terms, jargon.
`VOICE_MCP_WHISPER_SERVER`	No	Set to 0 to always use whisper-cli, with no warm server.	1
`VOICE_MCP_MAX_SPEAK_WORDS`	No	Longer text is cut at a sentence boundary ("the rest is on screen").	120
`VOICE_MCP_SPEECH_MARGIN_DB`	No	How much louder than room noise counts as speech. Raise it in noisy rooms.	12
`VOICE_MCP_MODEL_SEARCH_PATHS`	No	Extra folders to check for an existing model (`:`-separated).
`VOICE_MCP_WHISPER_MODEL_PATH`	No	Use this exact ggml-*.bin file.
`VOICE_MCP_SERVER_IDLE_MINUTES`	No	How long the warm server stays up without use.	15
`VOICE_MCP_START_TIMEOUT_SECONDS`	No	How long to wait for you to start talking.	8

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": true }
`prompts`	{ "listChanged": true }

Tools

Functions exposed to the LLM to take actions

Name Description

Name	Description
speak_and_listenA	Say something out loud to the user and hear their spoken reply. Speaks text_to_speak through the computer's speakers, then listens like a conversation turn — it waits for the user to start talking and stops when they finish — and returns an on-device transcript of what they said. Write text_to_speak for the ear, not the screen: 1–3 short sentences, under ~40 words; lead with the outcome, then one question. Plain words only: no markdown, bullets, emoji, code, file paths, URLs, stack traces or tables. Describe code instead of reading it ("I added a retry to the upload function"), say file names not paths ("in index.ts"), round numbers ("about two hundred ms"), spell out symbols. Ask one question at a time, answerable in a few words ("Should I deploy it — yes or no?"). Put the details (diffs, logs, links) in your normal on-screen reply, and say so out loud. Good: "The build passed and all tests are green. Want me to open the pull request?" Bad: "## Results\n- `npm test` ✅ 42/42\n- see /Users/x/repo/src/index.ts:120" Once the user is talking with you by voice, keep the conversation in voice: answer each transcript with another speak_and_listen call (not a text reply) until they say stop or start typing. A reply of "(No speech detected …)" means the user did not answer — never treat it as consent. If it reports that voice-mcp is not set up, call voice_setup.
voice_setupA	Check whether this computer has everything speak_and_listen needs — text-to-speech, a microphone recorder (SoX), whisper.cpp speech-to-text and the speech model — and optionally install what's missing. Anything already installed is reused (an existing model elsewhere on disk is symlinked, not re-downloaded). Call it with install=false (the default) first and tell the user what is missing. Only call it with install=true after the user agrees: it runs `brew install` for the missing packages and downloads the speech model once. It never uninstalls or changes anything else. If it reports INSTALLING, the install continues in the background — wait a minute and call it again to check.

speak_and_listenA

Say something out loud to the user and hear their spoken reply. Speaks text_to_speak through the computer's speakers, then listens like a conversation turn — it waits for the user to start talking and stops when they finish — and returns an on-device transcript of what they said.

Write text_to_speak for the ear, not the screen:

1–3 short sentences, under ~40 words; lead with the outcome, then one question.
Plain words only: no markdown, bullets, emoji, code, file paths, URLs, stack traces or tables.
Describe code instead of reading it ("I added a retry to the upload function"), say file names not paths ("in index.ts"), round numbers ("about two hundred ms"), spell out symbols.
Ask one question at a time, answerable in a few words ("Should I deploy it — yes or no?").
Put the details (diffs, logs, links) in your normal on-screen reply, and say so out loud.

Good: "The build passed and all tests are green. Want me to open the pull request?" Bad: "## Results\n- npm test ✅ 42/42\n- see /Users/x/repo/src/index.ts:120"

Once the user is talking with you by voice, keep the conversation in voice: answer each transcript with another speak_and_listen call (not a text reply) until they say stop or start typing. A reply of "(No speech detected …)" means the user did not answer — never treat it as consent. If it reports that voice-mcp is not set up, call voice_setup.

voice_setupA

Check whether this computer has everything speak_and_listen needs — text-to-speech, a microphone recorder (SoX), whisper.cpp speech-to-text and the speech model — and optionally install what's missing. Anything already installed is reused (an existing model elsewhere on disk is symlinked, not re-downloaded). Call it with install=false (the default) first and tell the user what is missing. Only call it with install=true after the user agrees: it runs brew install for the missing packages and downloads the speech model once. It never uninstalls or changes anything else. If it reports INSTALLING, the install continues in the background — wait a minute and call it again to check.

Prompts

Interactive templates invoked by user choice

Name	Description
`setup`	Check what voice-mcp needs, install what's missing (with your OK), then test it.
`voice_mode`	Hands-free session: Claude checks in out loud via speak_and_listen, using speakable phrasing.

Resources

Contextual data attached and managed by the client

Name	Description
No resources

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.8/5.0

Scored 2026-09-23 20:05 across 2 tools

Disambiguation5/5

The two tools are completely distinct: speak_and_listen handles interactive voice turns, while voice_setup handles environment setup and installation. There is no overlap in purpose or timing.

Naming Consistency4/5

Both names use snake_case and are descriptive, but speak_and_listen is a verb phrase while voice_setup is a noun compound. The pattern is mostly consistent with a minor structural deviation.

Tool Count4/5

Two tools is sparse but appropriate for the narrow scope of Mac voice interaction and setup. Each tool serves a clear, necessary role and there are no redundant tools.

Completeness4/5

The core voice turn-taking flow and the setup prerequisites are fully covered. Minor gaps like standalone listening or granular audio controls exist but do not affect the primary use case.

Resources

GitHub Repository

Need Help?

Related Servers