feat(bridge): gate Whisper behind Silero VAD; harden broadcast auto-start

Address review of the noise/broadcast fixes:

- STT now refuses to run Whisper on non-speech. transcribe() runs the Silero
  VAD (bundled with faster-whisper, no new dep) BEFORE the model, so noise or a
  brief loud blip with no real speech never reaches STT and can't be
  hallucinated into a transcript. The no_speech_prob/avg_logprob post-filter
  stays as a second line of defence (a clap the VAD lets through is still killed
  by Whisper's own no_speech_prob). VAD is env-tunable (VAD_THRESHOLD,
  VAD_MIN_SPEECH_MS, VAD_ENABLED) and fail-open so a VAD error never swallows a
  real utterance. Validated on real audio: synthesised Korean speech passes;
  silence, a 50ms blip and white noise are rejected.

- Broadcast auto-start no longer blocks the voice join and no longer silently
  swallows failures: wiring is synchronous, the Go-Live start runs in the
  background with a bounded retry and a loud final-failure log.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

bridge/server.py

@@ -51,10 +51,10 @@ from flask import Flask, request, jsonify, Response, stream_with_context
 
 try:  # package-relative when imported as ``bridge.server``
     from bridge.text_utils import split_sentences
-    from bridge.stt_filter import filter_speech_segments
+    from bridge.stt_filter import filter_speech_segments, has_speech
 except ImportError:  # script-relative when run as ``bridge/server.py``
     from text_utils import split_sentences
-    from stt_filter import filter_speech_segments
+    from stt_filter import filter_speech_segments, has_speech
 
 app = Flask(__name__)
 
@@ -66,6 +66,15 @@ BRIDGE_PORT = int(os.environ.get("BRIDGE_PORT", "8765"))
 BRAIN_ENABLED = os.environ.get("JARVIS_BRAIN_ENABLED", "1") not in ("0", "false", "False")
 TTS_ENABLED = os.environ.get("JARVIS_TTS_ENABLED", "1") not in ("0", "false", "False")
 
+# Pre-STT speech gate (Silero VAD). Tunable for the Discord mic without a code
+# change: raise VAD_THRESHOLD to reject more noise, lower it to catch quieter
+# speech. VAD_MIN_SPEECH_MS is the shortest run of speech that counts (a brief
+# loud blip shorter than this never reaches Whisper). Set VAD_ENABLED=0 to fall
+# back to the old behaviour (always transcribe, rely on the post-filter only).
+VAD_ENABLED = os.environ.get("VAD_ENABLED", "1") not in ("0", "false", "False")
+VAD_THRESHOLD = float(os.environ.get("VAD_THRESHOLD", "0.4"))
+VAD_MIN_SPEECH_MS = int(os.environ.get("VAD_MIN_SPEECH_MS", "200"))
+
 # TTS engine: "melo" (MeloTTS Korean speaker, the warm worker) is the primary
 # voice; Piper is kept as a fallback if the worker is unreachable. Set
 # TTS_ENGINE=piper to disable MeloTTS entirely.
@@ -184,10 +193,25 @@ def transcribe(wav_bytes: bytes) -> dict:
             x_old = np.linspace(0.0, 1.0, num=audio.size, endpoint=False)
             x_new = np.linspace(0.0, 1.0, num=n_out, endpoint=False)
             audio = np.interp(x_new, x_old, audio).astype(np.float32)
+    # Pre-STT speech gate: don't even invoke Whisper unless there is real speech
+    # in the clip. Noise or a brief loud blip (no actual speech) is dropped here,
+    # before transcription, so the model never gets a chance to hallucinate a
+    # phrase from it. Fail-open inside has_speech() keeps a real utterance from
+    # being swallowed if the VAD is unavailable.
+    if VAD_ENABLED and not has_speech(
+        audio,
+        16000,
+        threshold=VAD_THRESHOLD,
+        min_speech_duration_ms=VAD_MIN_SPEECH_MS,
+        log=lambda m: print(f"[bridge] {m}", flush=True),
+    ):
+        print("[bridge] no speech detected (VAD) — skipping STT", flush=True)
+        return {"text": "", "language": None}
+
     segments, info = _whisper.transcribe(audio, beam_size=1)
-    # Speech gate: drop non-speech / hallucinated segments so a brief loud sound
-    # or background noise (mic blip with no real speech) does not become a
-    # transcript and make the bot reply to nothing. Mirrors the desktop
+    # Second line of defence: even speech-like audio (e.g. a clap the VAD let
+    # through) can make Whisper hallucinate, so drop non-speech / low-confidence
+    # segments by Whisper's own no_speech_prob + avg_logprob. Mirrors the desktop
     # listener's policy, driven by the same config thresholds.
     no_speech_threshold = getattr(_cfg, "whisper_no_speech_threshold", 0.5)
     min_confidence = getattr(_cfg, "whisper_min_confidence", 0.3)

bridge/stt_filter.py

@@ -25,6 +25,49 @@ from __future__ import annotations
 from typing import Callable, Optional
 
 
+def has_speech(
+    audio,
+    sampling_rate: int = 16000,
+    *,
+    threshold: float = 0.4,
+    min_speech_duration_ms: int = 200,
+    min_silence_duration_ms: int = 100,
+    log: Optional[Callable[[str], None]] = None,
+) -> bool:
+    """Pre-STT speech gate: ``True`` only if there is at least one real speech
+    region in ``audio`` (16 kHz mono float32).
+
+    This runs BEFORE Whisper so the model is never invoked on pure noise or a
+    brief loud blip (a clap, a key clack, a mic pop) that momentarily opened the
+    voice gate without anyone speaking. It uses the Silero VAD bundled with
+    faster-whisper (no extra dependency). The threshold is deliberately a little
+    below the faster-whisper default (0.5) so quiet but real speech is not
+    dropped; precision against confident noise-hallucinations is provided by the
+    downstream ``filter_speech_segments`` no_speech_prob gate.
+
+    Fail-open: if the VAD is unavailable or errors, return ``True`` so STT still
+    runs rather than silently swallowing a real utterance.
+    """
+    try:
+        from faster_whisper.vad import get_speech_timestamps, VadOptions
+    except Exception:  # VAD not available in this build -> don't block STT
+        return True
+    try:
+        if getattr(audio, "size", 1) == 0:
+            return False
+        opts = VadOptions(
+            threshold=threshold,
+            min_speech_duration_ms=min_speech_duration_ms,
+            min_silence_duration_ms=min_silence_duration_ms,
+        )
+        timestamps = get_speech_timestamps(audio, opts, sampling_rate)
+        return len(timestamps) > 0
+    except Exception as e:  # pragma: no cover - defensive
+        if log:
+            log(f"VAD check failed, falling back to STT: {e}")
+        return True
+
+
 def is_non_speech(no_speech_prob: float, threshold: float) -> bool:
     """True when Whisper flags a segment as non-speech (``>= threshold``)."""
     return no_speech_prob >= threshold