diff --git a/cli.py b/cli.py
index 4b315f9b6..18aeb2716 100644
--- a/cli.py
+++ b/cli.py
@@ -7414,11 +7414,12 @@ class HermesCLI:
             self._voice_stop_and_transcribe()
 
         # Audio cue: single beep BEFORE starting stream (avoid CoreAudio conflict)
-        try:
-            from tools.voice_mode import play_beep
-            play_beep(frequency=880, count=1)
-        except Exception:
-            pass
+        if self._voice_beeps_enabled():
+            try:
+                from tools.voice_mode import play_beep
+                play_beep(frequency=880, count=1)
+            except Exception:
+                pass
 
         try:
             self._voice_recorder.start(on_silence_stop=_on_silence)
@@ -7466,11 +7467,12 @@ class HermesCLI:
             wav_path = self._voice_recorder.stop()
 
             # Audio cue: double beep after stream stopped (no CoreAudio conflict)
-            try:
-                from tools.voice_mode import play_beep
-                play_beep(frequency=660, count=2)
-            except Exception:
-                pass
+            if self._voice_beeps_enabled():
+                try:
+                    from tools.voice_mode import play_beep
+                    play_beep(frequency=660, count=2)
+                except Exception:
+                    pass
 
             if wav_path is None:
                 _cprint(f"{_DIM}No speech detected.{_RST}")
@@ -7621,6 +7623,17 @@ class HermesCLI:
             _cprint(f"Unknown voice subcommand: {subcommand}")
             _cprint("Usage: /voice [on|off|tts|status]")
 
+    def _voice_beeps_enabled(self) -> bool:
+        """Return whether CLI voice mode should play record start/stop beeps."""
+        try:
+            from hermes_cli.config import load_config
+            voice_cfg = load_config().get("voice", {})
+            if isinstance(voice_cfg, dict):
+                return bool(voice_cfg.get("beep_enabled", True))
+        except Exception:
+            pass
+        return True
+
     def _enable_voice_mode(self):
         """Enable voice mode after checking requirements."""
         if self._voice_mode:
diff --git a/hermes_cli/config.py b/hermes_cli/config.py
index 5f10f0de2..b1566a2a5 100644
--- a/hermes_cli/config.py
+++ b/hermes_cli/config.py
@@ -645,6 +645,7 @@ DEFAULT_CONFIG = {
         "record_key": "ctrl+b",
         "max_recording_seconds": 120,
         "auto_tts": False,
+        "beep_enabled": True,         # Play record start/stop beeps in CLI voice mode
         "silence_threshold": 200,     # RMS below this = silence (0-32767)
         "silence_duration": 3.0,      # Seconds of silence before auto-stop
     },
@@ -849,7 +850,7 @@ DEFAULT_CONFIG = {
     },
 
     # Config schema version - bump this when adding new required fields
-    "_config_version": 21,
+    "_config_version": 22,
 }
 
 # =============================================================================
diff --git a/tests/tools/test_voice_cli_integration.py b/tests/tools/test_voice_cli_integration.py
index da500996a..e7d8811e0 100644
--- a/tests/tools/test_voice_cli_integration.py
+++ b/tests/tools/test_voice_cli_integration.py
@@ -933,6 +933,58 @@ class TestEnableVoiceModeReal:
         assert cli._voice_mode is True
 
 
+class TestVoiceBeepConfigReal:
+    """Tests the CLI voice beep toggle."""
+
+    @patch("hermes_cli.config.load_config", return_value={"voice": {}})
+    def test_beeps_enabled_by_default(self, _cfg):
+        cli = _make_voice_cli()
+        assert cli._voice_beeps_enabled() is True
+
+    @patch("hermes_cli.config.load_config", return_value={"voice": {"beep_enabled": False}})
+    def test_beeps_can_be_disabled(self, _cfg):
+        cli = _make_voice_cli()
+        assert cli._voice_beeps_enabled() is False
+
+    @patch("cli._cprint")
+    @patch("cli.threading.Thread")
+    @patch("tools.voice_mode.play_beep")
+    @patch("tools.voice_mode.create_audio_recorder")
+    @patch(
+        "tools.voice_mode.check_voice_requirements",
+        return_value={
+            "available": True,
+            "audio_available": True,
+            "stt_available": True,
+            "details": "OK",
+            "missing_packages": [],
+        },
+    )
+    @patch(
+        "hermes_cli.config.load_config",
+        return_value={
+            "voice": {
+                "beep_enabled": False,
+                "silence_threshold": 200,
+                "silence_duration": 3.0,
+            }
+        },
+    )
+    def test_start_recording_skips_beep_when_disabled(
+        self, _cfg, _req, mock_create, mock_beep, mock_thread, _cp
+    ):
+        recorder = MagicMock()
+        recorder.supports_silence_autostop = True
+        mock_create.return_value = recorder
+        mock_thread.return_value = MagicMock(start=MagicMock())
+
+        cli = _make_voice_cli()
+        cli._voice_start_recording()
+
+        recorder.start.assert_called_once()
+        mock_beep.assert_not_called()
+
+
 class TestDisableVoiceModeReal:
     """Tests _disable_voice_mode with real CLI instance."""
 
@@ -1087,6 +1139,16 @@ class TestVoiceStopAndTranscribeReal:
         cli._voice_stop_and_transcribe()
         assert cli._pending_input.empty()
 
+    @patch("cli._cprint")
+    @patch("hermes_cli.config.load_config", return_value={"voice": {"beep_enabled": False}})
+    @patch("tools.voice_mode.play_beep")
+    def test_no_speech_detected_skips_beep_when_disabled(self, mock_beep, _cfg, _cp):
+        recorder = MagicMock()
+        recorder.stop.return_value = None
+        cli = _make_voice_cli(_voice_recording=True, _voice_recorder=recorder)
+        cli._voice_stop_and_transcribe()
+        mock_beep.assert_not_called()
+
     @patch("cli._cprint")
     @patch("cli.os.unlink")
     @patch("cli.os.path.isfile", return_value=True)
diff --git a/website/docs/guides/use-voice-mode-with-hermes.md b/website/docs/guides/use-voice-mode-with-hermes.md
index 42b335559..d43c0a018 100644
--- a/website/docs/guides/use-voice-mode-with-hermes.md
+++ b/website/docs/guides/use-voice-mode-with-hermes.md
@@ -164,6 +164,7 @@ voice:
   record_key: "ctrl+b"
   max_recording_seconds: 120
   auto_tts: false
+  beep_enabled: true
   silence_threshold: 200
   silence_duration: 3.0
 
diff --git a/website/docs/user-guide/configuration.md b/website/docs/user-guide/configuration.md
index 4eb0c56d9..c6afd8332 100644
--- a/website/docs/user-guide/configuration.md
+++ b/website/docs/user-guide/configuration.md
@@ -1049,6 +1049,7 @@ voice:
   record_key: "ctrl+b"         # Push-to-talk key inside the CLI
   max_recording_seconds: 120    # Hard stop for long recordings
   auto_tts: false               # Enable spoken replies automatically when /voice on
+  beep_enabled: true            # Play record start/stop beeps in CLI voice mode
   silence_threshold: 200        # RMS threshold for speech detection
   silence_duration: 3.0         # Seconds of silence before auto-stop
 ```
diff --git a/website/docs/user-guide/features/voice-mode.md b/website/docs/user-guide/features/voice-mode.md
index 2befd59e0..b82718cf0 100644
--- a/website/docs/user-guide/features/voice-mode.md
+++ b/website/docs/user-guide/features/voice-mode.md
@@ -149,7 +149,7 @@ Two-stage algorithm detects when you've finished speaking:
 
 If no speech is detected at all for 15 seconds, recording stops automatically.
 
-Both `silence_threshold` and `silence_duration` are configurable in `config.yaml`.
+Both `silence_threshold` and `silence_duration` are configurable in `config.yaml`. You can also disable the record start/stop beeps with `voice.beep_enabled: false`.
 
 ### Streaming TTS
 
@@ -383,6 +383,7 @@ voice:
   record_key: "ctrl+b"            # Key to start/stop recording
   max_recording_seconds: 120       # Maximum recording length
   auto_tts: false                  # Auto-enable TTS when voice mode starts
+  beep_enabled: true               # Play record start/stop beeps
   silence_threshold: 200           # RMS level (0-32767) below which counts as silence
   silence_duration: 3.0            # Seconds of silence before auto-stop