Add X-VC voice conversion mode

platform/docker/profile-controller/profile_controller.py

@@ -34,6 +34,8 @@ SEPARATOR_LABEL_KEY = "com.mike-ai.stem-separator"
 SEPARATOR_WORKER = os.environ.get("SEPARATOR_WORKER", "").strip()
 VOICE_LABEL_KEY = "com.mike-ai.voice-worker"
 VOICE_WORKER = os.environ.get("VOICE_WORKER", "").strip()
+VOICE_CHANGE_LABEL_KEY = "com.mike-ai.voice-change-worker"
+VOICE_CHANGE_WORKER = os.environ.get("VOICE_CHANGE_WORKER", "").strip()
 LOCK = threading.Lock()
 log = logging.getLogger("profile-controller")
 
@@ -135,6 +137,17 @@ def voice_container() -> dict:
     return matches[0]
 
 
+def voice_change_container() -> dict:
+    if not VOICE_CHANGE_WORKER:
+        raise RuntimeError("voice-change worker is not configured")
+    matches = [item for item in labelled_containers(VOICE_CHANGE_LABEL_KEY)
+               if item.get("Labels", {}).get(VOICE_CHANGE_LABEL_KEY) == VOICE_CHANGE_WORKER]
+    if len(matches) != 1:
+        raise RuntimeError(
+            f"expected exactly one voice-change worker {VOICE_CHANGE_WORKER!r}, found {len(matches)}")
+    return matches[0]
+
+
 def stop_music_if_configured() -> None:
     if MUSIC_WORKER:
         stop_container(music_container(), timeout=30)
@@ -150,6 +163,11 @@ def stop_voice_if_configured() -> None:
         stop_container(voice_container(), timeout=30)
 
 
+def stop_voice_change_if_configured() -> None:
+    if VOICE_CHANGE_WORKER:
+        stop_container(voice_change_container(), timeout=30)
+
+
 def stop_container(item: dict, timeout: int = 120) -> None:
     if item.get("State") != "running":
         return
@@ -190,6 +208,7 @@ def set_image_worker(running: bool, kind: str = IMAGE_WORKER) -> dict:
             stop_music_if_configured()
             stop_separator_if_configured()
             stop_voice_if_configured()
+            stop_voice_change_if_configured()
             for other in image_containers():
                 if other["Id"] != item["Id"]:
                     stop_container(other, timeout=20)
@@ -217,6 +236,7 @@ def set_music_worker(running: bool) -> dict:
             stop_container(tts_container(), timeout=30)
             stop_separator_if_configured()
             stop_voice_if_configured()
+            stop_voice_change_if_configured()
             start_container(item)
         else:
             stop_container(item, timeout=30)
@@ -236,6 +256,7 @@ def set_separator_worker(running: bool) -> dict:
             stop_container(tts_container(), timeout=30)
             stop_music_if_configured()
             stop_voice_if_configured()
+            stop_voice_change_if_configured()
             start_container(item)
         else:
             stop_container(item, timeout=30)
@@ -244,7 +265,7 @@ def set_separator_worker(running: bool) -> dict:
 
 
 def set_voice_worker(running: bool) -> dict:
-    """Start Vevo2 exclusively, or stop it before LLM restoration."""
+    """Start OmniVoice exclusively, or stop it before LLM restoration."""
     with LOCK:
         item = voice_container()
         if running:
@@ -255,6 +276,7 @@ def set_voice_worker(running: bool) -> dict:
             stop_container(tts_container(), timeout=30)
             stop_music_if_configured()
             stop_separator_if_configured()
+            stop_voice_change_if_configured()
             start_container(item)
         else:
             stop_container(item, timeout=30)
@@ -262,6 +284,26 @@ def set_voice_worker(running: bool) -> dict:
                 "state": "running" if running else "stopped"}
 
 
+def set_voice_change_worker(running: bool) -> dict:
+    """Start X-VC exclusively, or stop it before another mode is loaded."""
+    with LOCK:
+        item = voice_change_container()
+        if running:
+            for profile_item in containers().values():
+                stop_container(profile_item)
+            for worker in image_containers():
+                stop_container(worker, timeout=20)
+            stop_container(tts_container(), timeout=30)
+            stop_music_if_configured()
+            stop_separator_if_configured()
+            stop_voice_if_configured()
+            start_container(item)
+        else:
+            stop_container(item, timeout=30)
+        return {"voice_change_worker": VOICE_CHANGE_WORKER,
+                "state": "running" if running else "stopped"}
+
+
 def active_profile(items: dict[str, dict] | None = None) -> str | None:
     items = items or containers()
     active = [name for name, item in items.items() if item.get("State") == "running"]
@@ -280,6 +322,7 @@ def activate(profile: str) -> dict:
         stop_music_if_configured()
         stop_separator_if_configured()
         stop_voice_if_configured()
+        stop_voice_change_if_configured()
         start_container(tts_container())
         items = containers()
         missing = [name for name in ALLOWED if name not in items]
@@ -365,6 +408,13 @@ class Handler(BaseHTTPRequestHandler):
                             "unhealthy" if "(unhealthy)" in voice_status else
                             "starting" if voice.get("State") == "running" else
                             "stopped")
+            voice_change = voice_change_container() if VOICE_CHANGE_WORKER else {}
+            voice_change_status = voice_change.get("Status", "")
+            voice_change_health = ("disabled" if not VOICE_CHANGE_WORKER else
+                                   "healthy" if "(healthy)" in voice_change_status else
+                                   "unhealthy" if "(unhealthy)" in voice_change_status else
+                                   "starting" if voice_change.get("State") == "running" else
+                                   "stopped")
             self.reply(200, {"active_profile": active_profile(items),
                              "music_worker": music.get("State", "disabled"),
                              "music_health": music_health,
@@ -372,6 +422,8 @@ class Handler(BaseHTTPRequestHandler):
                              "separator_health": separator_health,
                              "voice_worker": voice.get("State", "disabled"),
                              "voice_health": voice_health,
+                             "voice_change_worker": voice_change.get("State", "disabled"),
+                             "voice_change_health": voice_change_health,
                              "profiles": {name: items.get(name, {}).get(
                                  "State", "missing") for name in ALLOWED}})
         except Exception as exc:
@@ -410,6 +462,13 @@ class Handler(BaseHTTPRequestHandler):
                 log.exception("voice worker transition failed")
                 self.reply(503, {"error": str(exc)})
             return
+        if self.path in {"/workers/voice-change/start", "/workers/voice-change/stop"}:
+            try:
+                self.reply(200, set_voice_change_worker(self.path.endswith("/start")))
+            except Exception as exc:
+                log.exception("voice-change worker transition failed")
+                self.reply(503, {"error": str(exc)})
+            return
         worker_paths = {
             "/workers/image/start": (IMAGE_WORKER, True),
             "/workers/image/stop": (IMAGE_WORKER, False),

platform/docker/wireguard-gateway/entrypoint.sh

@@ -82,6 +82,7 @@ start_proxy 7861 music-ui:3000
 start_proxy 7862 music-worker:7860
 start_proxy 8007 stem-separator:8080
 start_proxy 8008 voice-studio:8008
+start_proxy 8009 xvc-studio:8009
 start_proxy 8202 mcp-athena-operator:8000
 start_proxy 9443 portainer:9443
 

platform/llama-dashboard/app.py

@@ -29,6 +29,7 @@ MUSIC_ORIGINAL_UI_URL = os.getenv(
 )
 SEPARATOR_UI_URL = os.getenv("SEPARATOR_UI_URL", "http://192.168.1.212:8007/")
 VOICE_UI_URL = os.getenv("VOICE_UI_URL", "http://192.168.1.212:8008/")
+VOICE_CHANGE_UI_URL = os.getenv("VOICE_CHANGE_UI_URL", "http://192.168.1.212:8009/")
 HOST_PROC = Path(os.getenv("HOST_PROC", "/host/proc"))
 HOST_DATA = os.getenv("HOST_DATA", "/host/data")
 HOST_MODELS = Path(os.getenv("HOST_MODELS", "/host/models"))
@@ -278,7 +279,7 @@ def router_status() -> tuple[dict[str, Any], str | None]:
 
 
 def change_mode(mode: str) -> tuple[int, dict[str, Any]]:
-    if mode not in {"llm", "music", "separation", "voice"}:
+    if mode not in {"llm", "music", "separation", "voice", "voicechange"}:
         return 400, {"error": "invalid mode"}
     headers = {"Accept": "application/json", "Content-Type": "application/json"}
     if ROUTER_API_KEY:
@@ -636,7 +637,7 @@ HTML = r'''<!doctype html>
 </style></head><body><main>
 <div class="top"><div><div class="eyebrow">Mike AI · Live Telemetry</div><h1>Athena llama.cpp Dashboard</h1></div><div class="live"><span class="dot" id="dot"></span><span id="updated">verbinde …</span></div></div>
 <section class="grid">
-  <article class="card span12"><div class="mode-row"><div><div class="label">Athena Betriebsmodus</div><div class="value" id="operatingMode">–</div><div class="sub" id="modeStatus">Status wird geladen …</div></div><div class="mode-buttons"><button id="llmMode" onclick="setMode('llm')">LLM-Betrieb</button><button id="musicMode" onclick="setMode('music')">Musikstudio</button><button id="separationMode" onclick="setMode('separation')">Audio trennen</button><button id="voiceMode" onclick="setMode('voice')">Voice Studio</button><span id="musicOpen" hidden><a class="stable" href="__MUSIC_ORIGINAL_UI_URL__" target="_blank" rel="noopener">Original UI · stabil</a><a class="experimental" href="__MUSIC_COMMUNITY_UI_URL__" target="_blank" rel="noopener">Community UI · experimentell</a></span><span id="separatorOpen" hidden><a class="stable" href="__SEPARATOR_UI_URL__" target="_blank" rel="noopener">Separator öffnen</a></span><span id="voiceOpen" hidden><a class="stable" href="__VOICE_UI_URL__" target="_blank" rel="noopener">Voice Studio öffnen</a></span></div></div></article>
+  <article class="card span12"><div class="mode-row"><div><div class="label">Athena Betriebsmodus</div><div class="value" id="operatingMode">–</div><div class="sub" id="modeStatus">Status wird geladen …</div></div><div class="mode-buttons"><button id="llmMode" onclick="setMode('llm')">LLM-Betrieb</button><button id="musicMode" onclick="setMode('music')">Musikstudio</button><button id="separationMode" onclick="setMode('separation')">Audio trennen</button><button id="voiceMode" onclick="setMode('voice')">Voice Studio</button><button id="voiceChangeMode" onclick="setMode('voicechange')">Voice Changer</button><span id="musicOpen" hidden><a class="stable" href="__MUSIC_ORIGINAL_UI_URL__" target="_blank" rel="noopener">Original UI · stabil</a><a class="experimental" href="__MUSIC_COMMUNITY_UI_URL__" target="_blank" rel="noopener">Community UI · experimentell</a></span><span id="separatorOpen" hidden><a class="stable" href="__SEPARATOR_UI_URL__" target="_blank" rel="noopener">Separator öffnen</a></span><span id="voiceOpen" hidden><a class="stable" href="__VOICE_UI_URL__" target="_blank" rel="noopener">Voice Studio öffnen</a></span><span id="voiceChangeOpen" hidden><a class="experimental" href="__VOICE_CHANGE_UI_URL__" target="_blank" rel="noopener">X-VC öffnen</a></span></div></div></article>
   <article class="card span3"><div class="label">Aktives Profil</div><div class="value" id="profile">–</div><div class="sub" id="profileSub">Router wird abgefragt</div></article>
   <article class="card span3"><div class="label">Modell</div><div class="value" id="model">–</div><div class="sub" id="modelSub">–</div></article>
   <article class="card span3"><div class="label">CPU</div><div class="value" id="cpu">–</div><div class="bar"><div class="fill" id="cpuBar"></div></div><div class="sub" id="load">–</div></article>
@@ -677,11 +678,30 @@ const imagePhaseLabel=p=>({"stopping-qwen":"Qwen wird entladen","loading-image":
 let modeBusy=false;
 async function setMode(mode){if(modeBusy)return;modeBusy=true;$('llmMode').disabled=$('musicMode').disabled=$('separationMode').disabled=$('voiceMode').disabled=true;$('modeStatus').textContent='Umschaltung angefordert …';try{let r=await fetch('/api/mode',{method:'POST',headers:{'Content-Type':'application/json'},body:JSON.stringify({mode})});let d=await r.json();if(!r.ok)throw Error(d?.error?.message||d?.error||`HTTP ${r.status}`);$('modeStatus').textContent='Umschaltung läuft …'}catch(e){$('modeStatus').textContent=e.message;$('modeStatus').classList.add('mode-error')}finally{modeBusy=false;setTimeout(refresh,250)}}
 async function refresh(){try{let r=await fetch('/api/status',{cache:'no-store'});if(!r.ok)throw Error(`HTTP ${r.status}`);let d=await r.json(),c=d.cpu||{},m=c.memory||{},rt=d.router||{},up=rt.upstream||{},q=rt.qwen||{},lr=d.llama_runtime||{},img=rt.image||{},imageActive=img.phase&&img.phase!=='idle';let md=rt.mode||{},switchingMode=md.phase&&md.phase!=='ready',modeName=md.active==='music'?'Musikstudio':md.active==='separation'?'Stimmtrennung':md.active==='voice'?'Voice Studio':'LLM-Betrieb';$('operatingMode').textContent=modeName;$('modeStatus').textContent=switchingMode?`Umschaltung: ${md.phase}`:(md.last_error||`Musik: ${md.music_worker||'–'} · Separator: ${md.separator_worker||'–'} · Voice: ${md.voice_worker||'–'}${md.return_profile?` · Rückkehr zu ${md.return_profile}`:''}`);$('modeStatus').classList.toggle('mode-error',!!md.last_error);$('llmMode').classList.toggle('active',md.active==='llm');$('musicMode').classList.toggle('active',md.active==='music');$('separationMode').classList.toggle('active',md.active==='separation');$('voiceMode').classList.toggle('active',md.active==='voice');$('llmMode').disabled=$('musicMode').disabled=$('separationMode').disabled=$('voiceMode').disabled=modeBusy||switchingMode||!md.enabled;$('musicOpen').hidden=md.active!=='music';$('separatorOpen').hidden=md.active!=='separation';$('voiceOpen').hidden=md.active!=='voice';$('profile').textContent=imageActive?'Bildgenerierung':(rt.current_profile||'nicht geladen');$('profileSub').textContent=imageActive?imagePhaseLabel(img.phase):(rt.switching?`Wechsel zu ${rt.switching}`:`Kontext: ${up.ctx?up.ctx.toLocaleString('de-DE'):'–'} Token`);$('model').textContent=imageActive?(img.model||'Bildmodell'):(up.model||'–');$('modelSub').textContent=imageActive?`${img.model_loaded?'geladen':'wird vorbereitet'} · Worker ${img.worker||'–'}`:(lr.model_file|| (up.reachable?'llama.cpp erreichbar':'llama.cpp nicht erreichbar'));$('cpu').textContent=pct(c.usage_percent);$('cpuBar').style.width=`${c.usage_percent||0}%`;$('load').textContent=`${c.logical_cpus||'–'} Threads · Load ${(c.load||[]).join(' / ')}`;let rp=m.total?m.used/m.total*100:0;$('ram').textContent=pct(rp);$('ramBar').style.width=`${rp}%`;$('ramSub').textContent=`${gib(m.used)} / ${gib(m.total)}`;$('gpuCards').innerHTML=(d.gpus||[]).map(gpuCard).join('')||'<article class="card span12 error">Keine GPU-Daten verfügbar</article>';$('availability').textContent=imageActive?imagePhaseLabel(img.phase):(q.available?'bereit':'nicht bereit');$('availability').className=`value status ${(imageActive||q.available)?'':'bad'}`;$('activeChats').textContent=q.active_chats??'–';$('routerUptime').textContent=dur(rt.uptime_seconds);$('switching').textContent=imageActive?imagePhaseLabel(img.phase):(rt.switching||'nein');let disk=c.disk_data||{},dp=disk.total?disk.used/disk.total*100:null;$('dataDisk').textContent=pct(dp);$('processes').innerHTML=(d.gpu_processes||[]).map(p=>`<tr><td>${(d.gpus||[]).find(g=>g.uuid===p.gpu_uuid)?.index??'–'}</td><td>${p.name}</td><td>${p.pid}</td><td>${p.memory_mib??'–'} MiB</td></tr>`).join('')||'<tr><td colspan="4">Keine Compute-Prozesse gemeldet</td></tr>';let runtime=[['Modell-Datei',lr.model_file],['PID',lr.pid],['Kontext',lr.context_size?lr.context_size.toLocaleString('de-DE'):'–'],['Batch / µBatch',`${lr.batch_size??'–'} / ${lr.ubatch_size??'–'}`],['Parallel',lr.parallel],['Threads',`${lr.threads??'–'} / ${lr.threads_batch??'–'}`],['Geräte',lr.device],['Tensor-Split',lr.tensor_split],['KV-Cache',`${lr.cache_k??'–'} / ${lr.cache_v??'–'}`],['Flash Attention',lr.flash_attention?'an':'aus'],['Prompt-Cache',lr.prompt_cache?'an':'aus'],['MTP Draft',lr.mtp_draft_tokens]];$('runtime').innerHTML=runtime.map(([k,v])=>`<div class="metric"><b>${v??'–'}</b><span>${k}</span></div>`).join('');let es=Object.entries(d.errors||{}).filter(([,v])=>v);$('errors').hidden=!es.length;$('errors').textContent=es.map(([k,v])=>`${k}: ${v}`).join('\n');$('updated').textContent=`Live · ${new Date(d.timestamp*1000).toLocaleTimeString('de-DE')}`;$('dot').style.background='var(--green)'}catch(e){$('updated').textContent=`Verbindung gestört: ${e.message}`;$('dot').style.background='var(--red)'}}refresh();setInterval(refresh,1000);
+</script><script>
+const baseSetMode=setMode;
+setMode=async function(mode){
+  if(modeBusy)return;
+  for(const id of ['llmMode','musicMode','separationMode','voiceMode','voiceChangeMode'])$(id).disabled=true;
+  await baseSetMode(mode);
+};
+async function refreshVoiceChange(){
+  try{
+    const response=await fetch('/api/status',{cache:'no-store'}); if(!response.ok)return;
+    const data=await response.json(),mode=data.router?.mode||{},active=mode.active==='voicechange';
+    $('voiceChangeMode').classList.toggle('active',active);
+    $('voiceChangeMode').disabled=modeBusy||(mode.phase&&mode.phase!=='ready')||!mode.enabled;
+    $('voiceChangeOpen').hidden=!active;
+    if(active)$('operatingMode').textContent='Voice Changer';
+  }catch(_error){}
+}
+setTimeout(()=>{refreshVoiceChange();setInterval(refreshVoiceChange,1000)},150);
 </script><script src="/full.js"></script><script src="/history.js"></script></body></html>'''.replace(
     "__MUSIC_ORIGINAL_UI_URL__", MUSIC_ORIGINAL_UI_URL
 ).replace("__MUSIC_COMMUNITY_UI_URL__", MUSIC_COMMUNITY_UI_URL
 ).replace("__SEPARATOR_UI_URL__", SEPARATOR_UI_URL
-).replace("__VOICE_UI_URL__", VOICE_UI_URL)
+).replace("__VOICE_UI_URL__", VOICE_UI_URL
+).replace("__VOICE_CHANGE_UI_URL__", VOICE_CHANGE_UI_URL)
 
 
 FULL_JS = r'''