Hitonabi/mission-control-v2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Feat: Sprechen-Tab — mit Hermes per Sprache reden (Browser-Voice + 3D-Avatar)

Browse Source 
Voll-Duplex Sprach-Interaktion vom lokalen PC mit dem vollen Hermes-Agenten
(api_server :8642, OpenAI-kompatibel → gleiche Tools + geteiltes Mem0 wie CLI/Telegram).

- Voice-Sidecar (voice_service/, eigenes Py3.12-venv ~/.voice, :8650): STT faster-whisper
  (medium, de) + gestuftes TTS — Piper (schnell, Default) + Chatterbox (premium, Voice-Cloning,
  lazy-load, CPU-Start). Analog mem0_service.
- Backend: routers/voice.py (Proxy /api/voice/stt|tts|voices + /chat-SSE an Hermes mit
  Bearer API_SERVER_KEY + X-Hermes-Session-Id für server-seitigen Verlauf). config.py:
  VOICE_SERVICE_URL + HERMES_API_KEY (Fallback aus ~/.hermes/.env). System-Dienstliste +
  Wartung (Restart/Logs) um voice-service ergänzt.
- Frontend: Sprechen-Tab mit 3D-Avatar (VRM via three-vrm) — Lippensync (Web-Audio-Pegel),
  Blinzeln, Sentiment-Mimik, Ruhepose. Avatar-Picker (CORS-freie Galerie + .vrm-Upload + URL
  + VRoid-Hub-Link) + Stimm-Auswahl. Push-to-talk (Knopf/Leertaste). Deps: three, r3f, drei.
- Deploy: deploy/voice-service.service + deploy.sh (idempotenter Sidecar-Install, enable, restart).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Hitonabi
2026-06-27 23:26:58 +02:00
parent 2360ad173a
commit 8e7ce1b1d3
22 changed files with 1887 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/routers/system.py
+10 -2
View File
@@ -14,7 +14,7 @@ from pydantic import BaseModel
import httpx
from config import GATEWAY_URL, HERMES_API_URL, LLAMA_SWAP_URL, MEM0_SERVICE_URL
from config import GATEWAY_URL, HERMES_API_URL, LLAMA_SWAP_URL, MEM0_SERVICE_URL, VOICE_SERVICE_URL
from services import backup as backup_svc
from services.agent import agent_status
from services.gateway import gateway_reachable
@@ -28,7 +28,7 @@ log = logging.getLogger(__name__)
router = APIRouter(prefix="/api")
# Nur diese User-Dienste dürfen neugestartet werden.
ALLOWED_SERVICES = {"mission-control-2", "hermes-gateway", "hermes-webui"}
ALLOWED_SERVICES = {"mission-control-2", "hermes-gateway", "hermes-webui", "mem0-service", "voice-service"}
# Quelle für Self-Update (auf der Box ~/mission-control-v2).
SOURCE_DIR = os.path.expanduser(os.environ.get("MC2_SOURCE_DIR", "~/mission-control-v2"))
@@ -45,6 +45,13 @@ def _mem0_reachable() -> bool:
return False
def _voice_reachable() -> bool:
try:
return httpx.get(f"{VOICE_SERVICE_URL}/health", timeout=2).status_code == 200
except Exception:
return False
@router.get("/system/services")
def services() -> dict:
"""Aggregierte Erreichbarkeit aller Stack-Dienste (für die Health-Anzeige)."""
@@ -57,6 +64,7 @@ def services() -> dict:
{"name": "Hermes-Gateway", "url": HERMES_API_URL, "ok": a["gateway_reachable"]},
{"name": "Hermes-Terminal", "url": a["terminal_url"], "ok": a["terminal_reachable"]},
{"name": "Mem0 (Gedächtnis)", "url": MEM0_SERVICE_URL, "ok": _mem0_reachable()},
{"name": "Voice (STT/TTS)", "url": VOICE_SERVICE_URL, "ok": _voice_reachable()},
],
"links": {
"engine_ui": f"{LLAMA_SWAP_URL}/ui",
backend/routers/voice.py
+130
View File
@@ -0,0 +1,130 @@
"""
Voice-Endpoints für „Mit Hermes reden" (Browser-Voice + 3D-Avatar).
Dünner Layer: STT/TTS werden zum Voice-Sidecar (:8650) geproxyt; der Chat geht an den
Hermes-`api_server` (:8642, OpenAI-kompatibel) — denselben vollen Agenten mit Tools +
geteiltem Mem0 wie CLI/Telegram. Mit stabilem `X-Hermes-Session-Id` hält die Plattform den
Transcript server-seitig, daher schickt der Client je Turn nur die neue User-Nachricht.
LAN-only (kein Token in der 2.0-Phase), wie die übrigen MC2-Endpoints.
"""
import logging
import httpx
from fastapi import APIRouter, File, Form, HTTPException, UploadFile
from fastapi.responses import Response, StreamingResponse
from pydantic import BaseModel
from config import HERMES_API_KEY, HERMES_API_MODEL, HERMES_API_URL, VOICE_SERVICE_URL
log = logging.getLogger(__name__)
router = APIRouter(prefix="/api")
_TIMEOUT = httpx.Timeout(120.0, connect=5.0) # Chatterbox-TTS auf CPU darf dauern
class TTSIn(BaseModel):
text: str
engine: str = "piper"
voice: str = ""
language: str = ""
ref_path: str = ""
class ChatIn(BaseModel):
text: str # die neue User-Äußerung (STT-Ergebnis)
session_id: str # stabiler Voice-Faden → server-seitiger Transcript
session_key: str = "" # optional: Langzeit-Memory-Scope
system: str = "" # optionaler ephemerer System-Prompt (z.B. „antworte knapp/gesprochen")
model: str = ""
@router.get("/voice/health")
def voice_health() -> dict:
"""Erreichbarkeit des Voice-Sidecars + ob der Hermes-API-Key gesetzt ist."""
out: dict = {"sidecar": False, "hermes_key": bool(HERMES_API_KEY)}
try:
r = httpx.get(f"{VOICE_SERVICE_URL}/health", timeout=httpx.Timeout(5.0))
out["sidecar"] = r.status_code == 200
out["detail"] = r.json() if r.status_code == 200 else None
except Exception as exc: # noqa: BLE001
out["error"] = str(exc)
return out
@router.get("/voice/voices")
def voice_voices() -> dict:
try:
r = httpx.get(f"{VOICE_SERVICE_URL}/voices", timeout=httpx.Timeout(10.0))
r.raise_for_status()
return r.json()
except Exception as exc: # noqa: BLE001
raise HTTPException(502, f"Voice-Sidecar nicht erreichbar: {exc}")
@router.post("/voice/stt")
async def voice_stt(audio: UploadFile = File(...), language: str = Form(default="")) -> dict:
"""Mikro-Audio → Text (Proxy auf Sidecar /stt)."""
data = await audio.read()
if not data:
raise HTTPException(400, "Leeres Audio.")
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})
r.raise_for_status()
return r.json()
except httpx.HTTPError as exc:
raise HTTPException(502, f"STT fehlgeschlagen: {exc}")
@router.post("/voice/tts")
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())
r.raise_for_status()
return Response(content=r.content, media_type=r.headers.get("content-type", "audio/wav"))
except httpx.HTTPError as exc:
raise HTTPException(502, f"TTS fehlgeschlagen: {exc}")
@router.post("/voice/chat")
async def voice_chat(body: ChatIn) -> StreamingResponse:
"""Neue User-Äußerung → Hermes-Agent (api_server, streamend). SSE wird 1:1 durchgereicht.
Mit `X-Hermes-Session-Id` hält die Plattform den Verlauf — wir senden nur die neue Nachricht.
Auth per Bearer (API_SERVER_KEY); ohne Key liefert :8642 ein 401."""
if not HERMES_API_KEY:
raise HTTPException(503, "HERMES_API_KEY/API_SERVER_KEY nicht gesetzt — Agent-Auth fehlt.")
messages = []
if body.system:
messages.append({"role": "system", "content": body.system})
messages.append({"role": "user", "content": body.text})
payload = {"model": body.model or HERMES_API_MODEL, "messages": messages, "stream": True}
headers = {
"Authorization": f"Bearer {HERMES_API_KEY}",
"X-Hermes-Session-Id": body.session_id,
}
if body.session_key:
headers["X-Hermes-Session-Key"] = body.session_key
async def gen():
try:
async with httpx.AsyncClient(timeout=httpx.Timeout(None, connect=5.0)) as client:
async with client.stream(
"POST", f"{HERMES_API_URL}/v1/chat/completions", json=payload, headers=headers,
) as r:
if r.status_code != 200:
detail = (await r.aread()).decode("utf-8", "replace")[:500]
yield f"data: {{\"error\": \"Hermes {r.status_code}: {detail}\"}}\n\n".encode()
return
async for chunk in r.aiter_raw():
yield chunk
except httpx.HTTPError as exc:
yield f"data: {{\"error\": \"Verbindung zu Hermes fehlgeschlagen: {exc}\"}}\n\n".encode()
return StreamingResponse(gen(), media_type="text/event-stream")