diff --git a/src/luke_scribe/api/routes/jobs.py b/src/luke_scribe/api/routes/jobs.py
index 2983b94..78069bb 100644
--- a/src/luke_scribe/api/routes/jobs.py
+++ b/src/luke_scribe/api/routes/jobs.py
@@ -168,6 +168,7 @@ def _to_status(job: Job) -> JobStatusResponse:
     return JobStatusResponse(
         job_id=job.id,
         status=job.status.value,
+        source_name=job.source_name,
         queue_position=job.queue_position,
         progress=job.progress,
         processed_sec=job.processed_sec,
diff --git a/src/luke_scribe/api/schemas.py b/src/luke_scribe/api/schemas.py
index 746d2cb..738f020 100644
--- a/src/luke_scribe/api/schemas.py
+++ b/src/luke_scribe/api/schemas.py
@@ -41,6 +41,7 @@ class JobCreateResponse(BaseModel):
 class JobStatusResponse(BaseModel):
     job_id: str
     status: str
+    source_name: str | None = None
     queue_position: int | None = None
     jobs_ahead: int | None = None
     progress: float | None = None
diff --git a/src/luke_scribe/api/static/dashboard.html b/src/luke_scribe/api/static/dashboard.html
index 0920664..93a1bb0 100644
--- a/src/luke_scribe/api/static/dashboard.html
+++ b/src/luke_scribe/api/static/dashboard.html
@@ -509,7 +509,7 @@ async function loadSystem() {
     $("#s-ct").textContent = b.compute_type_used || "—";
     $("#s-workers").textContent = b.workers ?? "—";
     $("#s-queue").textContent = b.queue_depth ?? "—";
-    $("#s-model").innerHTML = (b.models || []).join("<br>");
+    $("#s-model").innerHTML = (b.models || []).map(esc).join("<br>");
     $("#sys-detail").textContent = JSON.stringify(b, null, 2);
   } catch (e) {
     $("#sys-hint").textContent = "⚠ " + e.message;
@@ -758,8 +758,15 @@ $("#rt-start").addEventListener("click", async () => {
     }
   };
   ws.onclose = () => {
-    if (rt && !rt.stopped) setRtStatus("연결 종료", "err");
     $("#rt-wave").classList.remove("live");
+    if (rt && !rt.stopped) {
+      setRtStatus("연결 종료", "err");
+      // 예기치 않은 종료 시 마이크/오디오 컨텍스트 정리
+      if (rt.stream) rt.stream.getTracks().forEach((t) => t.stop());
+      if (rt.ctx) rt.ctx.close().catch(() => {});
+      $("#rt-start").disabled = false;
+      $("#rt-stop").disabled = true;
+    }
   };
   ws.onerror = () => setRtStatus("WebSocket 오류", "err");
 
@@ -781,7 +788,8 @@ $("#rt-start").addEventListener("click", async () => {
       if (ws.readyState === WebSocket.OPEN) ws.send(toPCM16(d));
     };
     src.connect(proc);
-    proc.connect(ctx.destination);
+    // proc.connect(ctx.destination) 의도적으로 생략 — 마이크 오디오를 스피커로
+    // 재생하면 에코 피드백이 생긴다 (ScriptProcessor는 연결 없이도 동작).
   } catch (e) {
     setRtStatus("오디오 캡처 실패: " + e.message, "err");
     stopRt();
diff --git a/src/luke_scribe/engine/owner.py b/src/luke_scribe/engine/owner.py
index 088819d..ac21f29 100644
--- a/src/luke_scribe/engine/owner.py
+++ b/src/luke_scribe/engine/owner.py
@@ -34,6 +34,27 @@ DOWNGRADE_CHAIN_GPU = ["float16", "int8_float16", "int8"]
 MAX_DOWNGRADES = 2
 
 
+# 무음 청크 decode 생략 임계 (int16 RMS, ~-36dBFS)
+SILENCE_RMS_THRESHOLD = 500.0
+
+
+def _rms16(data: bytes) -> float:
+    """PCM16 바이트의 RMS 레벨 (int16 단위, 0~32767)."""
+    import array
+
+    if not data:
+        return 0.0
+    usable = data[: len(data) - (len(data) % 2)]
+    samples = array.array("h")
+    samples.frombytes(usable)
+    if not samples:
+        return 0.0
+    s = 0.0
+    for v in samples:
+        s += v * v
+    return (s / len(samples)) ** 0.5
+
+
 def _pcm16_to_wav(data: bytes, sample_rate: int = 16000) -> bytes:
     """PCM16(mono) 바이트 → WAV(RIFF) 컨테이너. 실시간 청크 decode용."""
     n = len(data)
@@ -179,13 +200,23 @@ class EngineOwner:
         청크 단위로 ``transcribe(lane="realtime")``를 호출해 세그먼트를
         반환한다 (§3.9a — 단일 GPU 락, 실시간 우선 채널). v0.1 스텁이었던
         실전 구현으로: 첫 가설은 모델 로드(다운로드)가 필요할 수 있다.
+        무음 청크(RMS < 임계)는 decode 없이 빈 가설을 반환해 Whisper의
+        무음 할루시네이션이 LocalAgreement를 통해 확정되는 것을 막는다.
         """
         from ..results.models import Segment
 
+        if _rms16(pcm_chunk) < SILENCE_RMS_THRESHOLD:
+            return {"segments": [], "audio_sec": len(pcm_chunk) / 2 / 16000}
+
         wav = _pcm16_to_wav(pcm_chunk)
         fd, path = tempfile.mkstemp(suffix=".wav")
         try:
-            with os.fdopen(fd, "wb") as f:
+            try:
+                f = os.fdopen(fd, "wb")
+            except Exception:
+                os.close(fd)  # fdopen 실패 시 fd 누수 방지
+                raise
+            with f:
                 f.write(wav)
             req = InferenceRequest(
                 audio_path=path,
diff --git a/tests/integration/test_api.py b/tests/integration/test_api.py
index 39e5412..f71e66c 100644
--- a/tests/integration/test_api.py
+++ b/tests/integration/test_api.py
@@ -147,7 +147,9 @@ class TestJobs:
         # 조회
         r = client.get(f"/v1/jobs/{job_id}", headers=headers)
         assert r.status_code == 200
-        assert r.json()["status"] == "queued"
+        body = r.json()
+        assert body["status"] == "queued"
+        assert body["source_name"] == "meeting.mp3"  # 대시보드 파일 컬럼용
 
         # 결과는 아직 없음
         r = client.get(f"/v1/jobs/{job_id}/result", headers=headers)
diff --git a/tests/unit/test_engine_owner.py b/tests/unit/test_engine_owner.py
index 9e3e9ce..463b917 100644
--- a/tests/unit/test_engine_owner.py
+++ b/tests/unit/test_engine_owner.py
@@ -87,12 +87,24 @@ def test_pcm16_to_wav_header():
     assert struct.unpack("<I", wav[40:44])[0] == 16000  # data 크기
 
 
+def test_emit_hypothesis_skips_silence():
+    """무음 청크는 decode 없이 빈 가설 반환 (할루시네이션 방지)."""
+    engine = _SegFakeEngine()
+    owner = _bare_owner(engine)
+    out = owner.emit_hypothesis(b"\x00\x00" * 16000)  # 완전 무음
+    assert out["segments"] == []
+    assert engine.path is None  # decode 미실행 → 임시 파일도 안 만듦
+
+
 def test_emit_hypothesis_decodes_chunk_and_cleans_temp():
     import os
+    import random
+    import struct
 
     engine = _SegFakeEngine()
     owner = _bare_owner(engine)
-    chunk = b"\x00\x00" * 16000  # 1초 PCM16
+    # 1초 PCM16 — RMS 게이트를 통과하는 유성 신호 (무음이면 decode가 생략됨)
+    chunk = b"".join(struct.pack("<h", random.randint(-6000, 6000)) for _ in range(16000))
     out = owner.emit_hypothesis(chunk)
     assert out["audio_sec"] == 1.0
     assert len(out["segments"]) == 1