mac-voice-mcp 0.3.0 → 0.3.1

package/CHANGELOG.md

@@ -5,6 +5,15 @@ The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and
 
 ## [Unreleased]
 
+## [0.3.1] - 2026-09-29
+
+### Fixed
+- **Recording broke on Macs without SoX when Bluetooth headphones were connected** ([#6](https://github.com/jeet0007/mac-voice-mcp/issues/6)). Every turn failed with "pure digital silence".
+  - The ffmpeg fallback now records from the input chosen in System Settings (`:default`) instead of device number 0. `VOICE_MCP_FFMPEG_DEVICE` still overrides it.
+  - `voice_setup` treats ffmpeg as a fallback, recommends SoX, and installs it with your OK.
+  - Silence recorded through ffmpeg now points at the input device and SoX, not only at mic permissions.
+- **`voice_setup` notices tools installed since the last check**, such as `brew install sox` run in a terminal, without restarting the app.
+
 ## [0.3.0] - 2026-09-28
 
 ### Added

package/README.md

@@ -123,7 +123,7 @@ Setup checks what's already there before it changes anything:
 | Needed | Provided by | If it's missing |
 |---|---|---|
 | Voice | macOS `say`, using the most natural voice installed | Nothing to do. For a far better voice, add a free Premium one (see below). |
-| Microphone capture | SoX (`rec`) | `brew install sox` |
+| Microphone capture | SoX (`rec`). ffmpeg works as a fallback, but setup recommends SoX | `brew install sox` |
 | Speech-to-text | whisper.cpp (`whisper-cli` and `whisper-server`, Metal-accelerated) | `brew install whisper-cpp` |
 | Speech model | `base.en`, ~140 MB | Downloaded once to `~/.cache/mac-voice-mcp/models/` |
 
@@ -235,7 +235,8 @@ Everything is optional. Set these in your client config's `"env": { … }` block
 | `VOICE_MCP_START_TIMEOUT_SECONDS` | `15` | How long to wait for you to start talking. |
 | `VOICE_MCP_SPEECH_MARGIN_DB` | `12` | How much louder than room noise counts as speech. Raise it in noisy rooms. |
 | `VOICE_MCP_MIN_SPEECH_DB` | `-48` | The quietest level that ever counts as speech (dBFS). |
-| `VOICE_MCP_RECORDER` | `auto` | `sox` or `ffmpeg` (`ffmpeg` is macOS only). |
+| `VOICE_MCP_RECORDER` | `auto` | `sox` or `ffmpeg` (`ffmpeg` is macOS only). `auto` uses SoX, falling back to ffmpeg. |
+| `VOICE_MCP_FFMPEG_DEVICE` | `:default` | Which input ffmpeg records from. `:default` follows System Settings; `:1` picks device 1 (list them with `ffmpeg -f avfoundation -list_devices true -i ""`). |
 
 **Speech-to-text**
 
@@ -272,7 +273,7 @@ Everything is optional. Set these in your client config's `"env": { … }` block
 | Symptom | Fix |
 |---|---|
 | "voice-mcp is not set up yet" | Ask Claude to *set up voice*, or run `npx -y mac-voice-mcp@latest setup`. |
-| "microphone returned pure digital silence" | macOS is blocking the mic for the host app. Go to **System Settings → Privacy & Security → Microphone**, enable Claude / Cursor / your terminal, then restart that app. |
+| "microphone returned pure digital silence" | macOS is blocking the mic for the host app. Go to **System Settings → Privacy & Security → Microphone**, enable Claude / Cursor / your terminal, then restart that app. If the message says it's recording with ffmpeg, the input device is the likelier cause: run `brew install sox`. |
 | No permission prompt ever appears | Run `tccutil reset Microphone <bundle id>` and restart the app. Running `test` in Terminal only gives permission to Terminal, not to Claude Desktop. |
 | It cuts me off while I'm thinking | Set `VOICE_MCP_END_SILENCE_MS=1800` (or up to `2500`). |
 | It never stops listening | The room is too noisy for the defaults. Set `VOICE_MCP_SPEECH_MARGIN_DB=18`, or use a headset. |

package/dist/config.js

@@ -58,8 +58,8 @@ export const CONFIG = {
     minSpeechDb: envNum("VOICE_MCP_MIN_SPEECH_DB", -48),
     /** Recorder: auto (SoX, else ffmpeg) | sox | ffmpeg. */
     recorder: (process.env.VOICE_MCP_RECORDER?.trim().toLowerCase() || "auto"),
-    /** ffmpeg avfoundation audio input (macOS fallback recorder). */
-    ffmpegDevice: process.env.VOICE_MCP_FFMPEG_DEVICE?.trim() || ":0",
+    /** ffmpeg avfoundation audio input (macOS fallback recorder). ":default" follows the input chosen in System Settings. */
+    ffmpegDevice: process.env.VOICE_MCP_FFMPEG_DEVICE?.trim() || ":default",
     // --- Speech-to-text
     /** whisper.cpp model name (tiny.en, base.en, small.en, large-v3-turbo-q5_0, ...). */
     modelName,

package/dist/setup.js

@@ -76,9 +76,21 @@ async function checkRequirements() {
             : { label: "Voice", status: "ok", detail: choice.label });
     }
     const rec = findRecorder();
-    checks.push(rec
-        ? { label: "Recorder", status: "ok", detail: describeRecorder(rec) }
-        : { label: "Recorder", status: brewing ? "installing" : "missing", detail: "SoX is not installed", brew: IS_WIN ? undefined : "sox" });
+    if (!rec) {
+        checks.push({ label: "Recorder", status: brewing ? "installing" : "missing", detail: "SoX is not installed", brew: IS_WIN ? undefined : "sox" });
+    }
+    else if (rec.kind === "ffmpeg" && CONFIG.recorder === "auto") {
+        // Works, but it's the fragile path: recommend SoX, which is what the turn-taking is tuned on.
+        checks.push({
+            label: "Recorder",
+            status: brewing ? "installing" : "optional",
+            detail: `${describeRecorder(rec)}, as a fallback. SoX is recommended: it's more reliable with Bluetooth headsets and other audio devices`,
+            brew: "sox",
+        });
+    }
+    else {
+        checks.push({ label: "Recorder", status: "ok", detail: describeRecorder(rec) });
+    }
     const cli = findWhisperCli();
     const server = findWhisperServer();
     if (cli || server) {
@@ -131,9 +143,11 @@ async function checkRequirements() {
  * @param onProgress optional heartbeat while waiting (used for MCP progress notifications).
  */
 export async function runSetupFlow(install, onProgress) {
+    resetWhichCache(); // see anything installed since the last check (e.g. `brew install sox` in a terminal)
     let checks = await checkRequirements();
     if (install) {
-        const formulae = [...new Set(checks.filter((c) => c.status === "missing" && c.brew).map((c) => c.brew))];
+        // Missing pieces, plus recommended ones (SoX when only ffmpeg is there): the user agreed to install.
+        const formulae = [...new Set(checks.filter((c) => (c.status === "missing" || c.status === "optional") && c.brew).map((c) => c.brew))];
         const brew = findBrew();
         if (formulae.length && brew && !running(brewJob))
             brewJob = startBrewInstall(brew, formulae);
@@ -157,7 +171,7 @@ export async function runSetupFlow(install, onProgress) {
     const lines = [
         `voice-mcp setup — ${ready ? "READY" : installing ? "INSTALLING" : "NOT READY"}`,
         "",
-        ...checks.map((c) => `${icon[c.status]} ${c.label}: ${c.detail}${c.brew && c.status === "missing" ? ` → brew install ${c.brew}` : ""}`),
+        ...checks.map((c) => `${icon[c.status]} ${c.label}: ${c.detail}${c.brew && c.status !== "ok" && c.status !== "installing" ? ` → brew install ${c.brew}` : ""}`),
         IS_MAC ? "• Microphone: macOS asks for permission the first time speak_and_listen listens — click Allow." : "",
     ];
     if (done.length)
@@ -169,6 +183,11 @@ export async function runSetupFlow(install, onProgress) {
     lines.push("");
     if (ready) {
         lines.push("Next: everything is in place — speak_and_listen is ready to use.");
+        const recommended = [...new Set(checks.filter((c) => c.status === "optional" && c.brew).map((c) => c.brew))];
+        if (recommended.length && !install && findBrew()) {
+            lines.push(`Recommended: ask the user whether to brew install ${recommended.join(" ")} (see • above). ` +
+                "Only if they agree, call voice_setup with install=true.");
+        }
         if (checks.some((c) => c.label === "Voice" && c.status === "optional")) {
             lines.push("Mention the optional voice tip (•) to the user once — it makes the voice sound far more natural. Nothing else to do.");
         }

package/dist/voice.js

@@ -6,7 +6,7 @@ import { chime, findRecorder, listenForTurn, MIC_PERMISSION_HINT, RECORDER_MISSI
 import { CONFIG, debug, DEFAULT_LISTEN_SECONDS, MAX_LISTEN_SECONDS, MAX_SPEAK_CHARS } from "./config.js";
 import { acquireMicLock, MicBusyError } from "./lock.js";
 import { ensureModel } from "./model.js";
-import { SetupError } from "./proc.js";
+import { resetWhichCache, SetupError } from "./proc.js";
 import { prepareSpeech } from "./speech-text.js";
 import { findWhisperCli, findWhisperServer, prewarm, STT_MISSING, transcribe } from "./stt.js";
 /** Everything speak_and_listen needs, checked before saying a word. Never installs anything. */
@@ -66,9 +66,16 @@ async function turn(textToSpeak, seconds, model, signal, onPhase) {
         debug("listen:", heard);
         const timing = (transcribedMs) => timingNote({ spokeMs: spoke, listenedMs: t1 - tListen, talkedSeconds: heard.speechSeconds, transcribedMs });
         if (heard.digitalSilence) {
+            resetWhichCache(); // if the user fixes it by installing SoX, the next turn picks it up
+            const viaFfmpeg = findRecorder()?.kind === "ffmpeg";
             return {
                 ok: false,
-                text: `The microphone returned pure digital silence, which usually means microphone access is blocked. ${MIC_PERMISSION_HINT}`,
+                text: viaFfmpeg
+                    ? "The microphone returned pure digital silence. voice-mcp is recording with ffmpeg because SoX isn't installed, " +
+                        "and ffmpeg may be using a silent or wrong input device (for example after connecting Bluetooth headphones). " +
+                        "Suggest `brew install sox` (or call voice_setup), then try again. If that doesn't help: " +
+                        MIC_PERMISSION_HINT
+                    : `The microphone returned pure digital silence, which usually means microphone access is blocked. ${MIC_PERMISSION_HINT}`,
                 notes,
             };
         }

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "mac-voice-mcp",
   "mcpName": "io.github.jeet0007/mac-voice-mcp",
-  "version": "0.3.0",
+  "version": "0.3.1",
   "description": "Talk with Claude out loud on your Mac: speaks with macOS `say`, listens for one natural conversational turn, and transcribes on-device with whisper.cpp. An MCP server.",
   "type": "module",
   "bin": {