{"report":{"v":1,"package":"mac-voice-mcp","version":"0.10.0","ranAt":"2026-11-16T11:42:50.997Z","install":{"ok":true,"bin":"mac-voice-mcp","integrity":"sha512-fp2WtCU4nZoRbUmjmZ5MfBMqJY0B9IpatbBR7OX28n+9mAjtG/o85q/cCdsXjILvp9Qf1n2cMN1jaAu7XhtlDw==","deps":1,"scripts":[],"bins":["mac-voice-mcp","voice-mcp"],"license":"MIT","engines":"node >=22","repository":"git+https://github.com/jeet0007/mac-voice-mcp.git"},"start":{"ok":true,"ms":110,"serverName":"voice-mcp","serverVersion":"0.10.0","protocol":"2025-06-18","stderr":"[voice-mcp] mac-voice-mcp v0.10.0 ready on stdio (model: base.en, language: en)\n"},"tools":[{"name":"speak_and_listen","description":"Say something out loud to the user and hear their spoken reply.\nSpeaks text_to_speak through the computer's speakers, then listens like a conversation turn — it waits for\nthe user to start talking and stops when they finish — and returns an on-device transcript of what they said.\n\nWrite text_to_speak for the ear, not the screen:\n- 1–3 short sentences, under ~40 words; lead with the outcome, then one question.\n- Plain words only: no markdown, bullets, emoji, code, file paths, URLs, stack traces or tables.\n- Describe code instead of reading it (\"I added a retry to the upload function\"), say file names\n  not paths (\"in index.ts\"), round numbers (\"about two hundred ms\"), spell out symbols.\n- Ask one question at a time, answerable in a few words (\"Should I deploy it — yes or no?\").\n- Put the details (diffs, logs, links) in your normal on-screen reply, and say so out loud.\n- Tool output (Bash stdout, file writes) is NOT the on-screen reply. Only your own assistant message text renders.\n- A spoken turn with no assistant message text shows the user nothing — never skip the on-screen reply.\n\nGood: \"The build passed and all tests are green. Want me to open the pull request?\"\nBad: \"## Results\\n- `npm test` ✅ 42/42\\n- see /Users/x/repo/src/index.ts:120\"\n\nOnce the user is talking with you by voice, keep the conversation in voice: answer each transcript with\nanother speak_and_listen call (not a text reply) until they say stop or start typing.\nTo end voice mode, or for a one-way announcement, pass listen: false: it returns at once and speaks while you work.\nA reply of \"(No speech detected …)\" means the user did not answer — never treat it as consent. Ask once more;\nif still nothing, stop and say on screen that voice mode is paused and they can type to carry on (not speak: the mic is off).\nThe \"voice-mcp timing\" line at the end is diagnostics: ignore it unless the user asks why things feel slow.\nIf it reports that voice-mcp is not set up, call voice_setup.","params":["text_to_speak","listen_seconds","listen"]},{"name":"call","description":"Start or end a call: a hands-free session where the microphone stays open and the user talks whenever they\nlike, like a phone call, until they hang up. action start takes the speaker and microphone and returns the\nrules of the call; it says nothing aloud, so greet the user yourself, once, in a few words, with say, then call\nlisten. action end hangs up (also happens when the user says \"hang up\" or \"bye Claude\", or after a long\nsilence). During the call, speak with say and hear the user with listen.","params":["action"]},{"name":"say","description":"During a call: say text out loud and return at once, so you carry on working while it plays.\nThe result includes anything the user said meanwhile. Only during a call: use speak_and_listen otherwise.\n\nWrite text for the ear, not the screen:\n- 1–3 short sentences, under ~40 words; lead with the outcome, then one question.\n- Plain words only: no markdown, bullets, emoji, code, file paths, URLs, stack traces or tables.\n- Describe code instead of reading it (\"I added a retry to the upload function\"), say file names\n  not paths (\"in index.ts\"), round numbers (\"about two hundred ms\"), spell out symbols.\n- Ask one question at a time, answerable in a few words (\"Should I deploy it — yes or no?\").\n- Put the details (diffs, logs, links) in your normal on-screen reply, and say so out loud.\n- Tool output (Bash stdout, file writes) is NOT the on-screen reply. Only your own assistant message text renders.\n- A spoken turn with no assistant message text shows the user nothing — never skip the on-screen reply.","params":["text"]},{"name":"listen","description":"During a call: return what the user has said since you last heard from them, at once if something is waiting,\notherwise wait up to wait_seconds (default and maximum 40) for their next words.\n\"(still on the call, nothing said)\" means nobody spoke yet: call listen again to keep waiting, or say something.\nOnce it reports that the call ended, don't call it again.","params":["wait_seconds"]},{"name":"flag","description":"Call only when the user explicitly asks to flag or report a bad voice turn; never on your own. Saves the last minute of what voice-mcp did (levels, why turns ended, whether speech finished: no transcripts) to a local file. Only works when the user turned the flight recorder on. Returns the file's path.","params":["note"]},{"name":"voice_setup","description":"Check whether this computer has everything speak_and_listen needs — text-to-speech, a microphone recorder (SoX),\nwhisper.cpp speech-to-text and the speech model — and optionally install what's missing.\nAnything already installed is reused (an existing model elsewhere on disk is symlinked, not re-downloaded).\nCall it with install=false (the default) first and tell the user what is missing.\nOnly call it with install=true after the user agrees: it runs `brew install` for the missing packages\nand downloads the speech model once. It never uninstalls or changes anything else.\nkokoro=true (also only after the user agrees) installs the optional Kokoro voice: more natural than the built-in one,\nruns on this Mac, about 1 GB on disk. Once installed it's used automatically; the built-in voice stays as the fallback.\nbubble=true (also only after the user agrees) builds the floating call bubble on this Mac with swiftc: a small window during calls with mute and hang up.\nIf it reports INSTALLING, the install continues in the background — wait a minute and call it again to check.","params":["install","kokoro","bubble"]}],"toolsHash":"030e9bf5541687c4a3a3b95d0af2f5710e101004b463aa27a77364a1f1f0ebdb","wrote":[],"host":{"commit":"eaaffffaf52255d1b77dc4aacffdfaf353f0c12c","run":"https://github.com/itsHaddad/bragproof/actions/runs/43857070216"},"network":{"names":["registry.npmjs.org"],"conns":[]}},"summary":{"outcome":"started","needs":[],"contacts":[],"flags":[],"tools":6,"wrote":0,"callsTried":0,"callsAnswered":0,"callContacts":[]},"history":[{"package":"mac-voice-mcp","version":"0.10.0","ranAt":"2026-11-16T11:42:50.997Z","outcome":"started","tools":6,"contacts":0,"flags":0,"serious":0,"toolsHash":"030e9bf5541687c4a3a3b95d0af2f5710e101004b463aa27a77364a1f1f0ebdb"},{"package":"mac-voice-mcp","version":"0.9.0","ranAt":"2026-11-12T17:58:46.073Z","outcome":"started","tools":5,"contacts":0,"flags":0,"serious":0,"toolsHash":"7290f47f3502f51b72c535189d7ae383f9e58e4454f7782df2952f1187716c72"}],"page":"https://bragproof.smaverk.com/r/mac-voice-mcp"}