diff --git a/backend/routers/voice.py b/backend/routers/voice.py
index 4f49713..72a7ceb 100644
--- a/backend/routers/voice.py
+++ b/backend/routers/voice.py
@@ -11,6 +11,7 @@ LAN-only (kein Token in der 2.0-Phase), wie die übrigen MC2-Endpoints.
 
 import logging
 import os
+import time
 
 import httpx
 from fastapi import APIRouter, File, Form, HTTPException, UploadFile
@@ -18,6 +19,7 @@ from fastapi.responses import Response, StreamingResponse
 from pydantic import BaseModel
 
 from config import HERMES_API_KEY, HERMES_API_MODEL, HERMES_API_URL, LLAMA_SWAP_URL, VOICE_SERVICE_URL
+from services.voice_metrics import Timer, get_metrics, record_stage  # Per-Stage-Latenz (C2)
 
 # Injection-Schutz (Stufe 0): guard.py liegt im mcp/-Verzeichnis. Per Pfad laden (eigene MC2-Venv).
 import sys as _sys
@@ -86,6 +88,13 @@ class ChatIn(BaseModel):
     images: list[str] = []          # optionale Bildschirm-Sicht: ein data:-URL je Monitor (Lucys „Augen")
 
 
+@router.get("/voice/metrics")
+def voice_metrics() -> dict:
+    """Per-Stage-Latenz (STT/Vision/Chat-TTFB/TTS) — rollende Statistik, macht die Voice-Pipeline
+    messbar (C2). Anzeige im Frontend-Overhaul (E)."""
+    return get_metrics()
+
+
 @router.get("/voice/health")
 def voice_health() -> dict:
     """Erreichbarkeit des Voice-Sidecars + ob der Hermes-API-Key gesetzt ist."""
@@ -118,7 +127,8 @@ async def voice_stt(audio: UploadFile = File(...), language: str = Form(default=
     files = {"audio": (audio.filename or "rec.webm", data, audio.content_type or "audio/webm")}
     try:
         async with httpx.AsyncClient(timeout=_TIMEOUT) as client:
-            r = await client.post(f"{VOICE_SERVICE_URL}/stt", files=files, data={"language": language})
+            with Timer("stt"):
+                r = await client.post(f"{VOICE_SERVICE_URL}/stt", files=files, data={"language": language})
             r.raise_for_status()
             return r.json()
     except httpx.HTTPError as exc:
@@ -166,7 +176,8 @@ async def voice_tts(body: TTSIn) -> Response:
     """Text → Sprache (Proxy auf Sidecar /tts), liefert WAV-Bytes."""
     try:
         async with httpx.AsyncClient(timeout=_TIMEOUT) as client:
-            r = await client.post(f"{VOICE_SERVICE_URL}/tts", json=body.model_dump())
+            with Timer("tts"):
+                r = await client.post(f"{VOICE_SERVICE_URL}/tts", json=body.model_dump())
             r.raise_for_status()
             return Response(content=r.content, media_type=r.headers.get("content-type", "audio/wav"))
     except httpx.HTTPError as exc:
@@ -190,7 +201,8 @@ async def voice_chat(body: ChatIn) -> StreamingResponse:
     if imgs:
         # Bildschirm-Sicht: erst das Vision-Modell die Monitore beschreiben lassen, dann die Beschreibung
         # als TEXT-Kontext an Hermes (Lucy antwortet mit vollem Hirn/Gedächtnis, sieht via besserem VL-Modell).
-        desc = await _describe_images(imgs, body.text)
+        with Timer("vision"):
+            desc = await _describe_images(imgs, body.text)
         if desc:
             safe_desc = wrap_untrusted(desc, "BILDSCHIRM")
             user_text = f"[Bildschirm-Sicht — das ist gerade auf dem/den Schirm(en) zu sehen:\n{safe_desc}\n]\n\n{body.text}"
@@ -204,6 +216,8 @@ async def voice_chat(body: ChatIn) -> StreamingResponse:
         headers["X-Hermes-Session-Key"] = body.session_key
 
     async def gen():
+        t0 = time.perf_counter()
+        first = True
         try:
             async with httpx.AsyncClient(timeout=httpx.Timeout(None, connect=5.0)) as client:
                 async with client.stream(
@@ -214,6 +228,9 @@ async def voice_chat(body: ChatIn) -> StreamingResponse:
                         yield f"data: {{\"error\": \"Hermes {r.status_code}: {detail}\"}}\n\n".encode()
                         return
                     async for chunk in r.aiter_raw():
+                        if first:  # Time-To-First-Byte des Hermes-Streams (gefühlte Lucy-Latenz)
+                            record_stage("chat_ttfb", (time.perf_counter() - t0) * 1000.0)
+                            first = False
                         yield chunk
         except httpx.HTTPError as exc:
             yield f"data: {{\"error\": \"Verbindung zu Hermes fehlgeschlagen: {exc}\"}}\n\n".encode()
diff --git a/backend/services/voice_metrics.py b/backend/services/voice_metrics.py
new file mode 100644
index 0000000..758b12b
--- /dev/null
+++ b/backend/services/voice_metrics.py
@@ -0,0 +1,68 @@
+"""
+Per-Stage-Latenz-Metriken für die Voice/Lucy-Pipeline.
+
+Misst die Server-seitige Dauer jeder Stufe (STT, Vision-Beschreibung, Chat-TTFB, TTS) und hält
+rollende Statistiken (avg/p50/p95/last) im Speicher. Macht aus Latenz-VERMUTUNGEN gemessene Fakten
+— die eigentliche Voraussetzung, um gezielt zu optimieren (Stufe 5/C2 des Reviews). Anzeige im
+Frontend-Overhaul (E) analog zur TokenPerformanceCard.
+
+In-Memory + thread-safe (keine Datei-I/O — Latenz-Telemetrie ist transient, Restart = Reset).
+"""
+
+import threading
+import time
+from collections import deque
+
+_LOCK = threading.Lock()
+_MAX = 200
+_STAGES: dict[str, deque] = {}
+
+# Bekannte Stufen (für stabile UI-Reihenfolge); unbekannte werden trotzdem erfasst.
+STAGES = ("stt", "vision", "chat_ttfb", "tts")
+
+
+def record_stage(stage: str, ms: float) -> None:
+    """Eine gemessene Stage-Dauer (ms) verbuchen. No-op bei negativen Werten."""
+    if ms is None or ms < 0:
+        return
+    with _LOCK:
+        dq = _STAGES.get(stage)
+        if dq is None:
+            dq = _STAGES[stage] = deque(maxlen=_MAX)
+        dq.append(float(ms))
+
+
+class Timer:
+    """Context-Manager: misst die verstrichene Zeit und verbucht sie auf `stage`.
+    Funktioniert um `await`-Aufrufe herum (enter → await → exit)."""
+
+    def __init__(self, stage: str) -> None:
+        self.stage = stage
+        self._t0 = 0.0
+
+    def __enter__(self) -> "Timer":
+        self._t0 = time.perf_counter()
+        return self
+
+    def __exit__(self, *exc) -> None:
+        record_stage(self.stage, (time.perf_counter() - self._t0) * 1000.0)
+
+
+def _summary(vals: list[float]) -> dict:
+    if not vals:
+        return {"count": 0}
+    s = sorted(vals)
+    n = len(s)
+    return {
+        "count": n,
+        "avg_ms": round(sum(s) / n, 1),
+        "p50_ms": round(s[n // 2], 1),
+        "p95_ms": round(s[min(n - 1, int(n * 0.95))], 1),
+        "last_ms": round(vals[-1], 1),
+    }
+
+
+def get_metrics() -> dict:
+    """Rollende Zusammenfassung je Stufe."""
+    with _LOCK:
+        return {stage: _summary(list(dq)) for stage, dq in _STAGES.items()}