From 8c5c884b4d7dd2ceb953133f68b948b9c6371f92 Mon Sep 17 00:00:00 2001
From: Roger Oriol <rogi23696@gmail.com>
Date: Wed, 29 Jul 2026 00:07:10 +0200
Subject: [PATCH] add stt and tts services

---
 llamacpp/deployment-stt.yaml | 97 ++++++++++++++++++++++++++++++++++++
 llamacpp/deployment-tts.yaml | 93 ++++++++++++++++++++++++++++++++++
 2 files changed, 190 insertions(+)
 create mode 100644 llamacpp/deployment-stt.yaml
 create mode 100644 llamacpp/deployment-tts.yaml

diff --git a/llamacpp/deployment-stt.yaml b/llamacpp/deployment-stt.yaml
new file mode 100644
index 0000000..1d955be
--- /dev/null
+++ b/llamacpp/deployment-stt.yaml
@@ -0,0 +1,97 @@
+# Wyoming Speech-to-Text (rhasspy/wyoming-whisper).
+#
+# Exposes the Wyoming protocol over TCP on port 10300 so Home Assistant's
+# Wyoming STT integration can stream audio and receive transcriptions. Uses
+# faster-whisper under the hood with the language pinned to Catalan (`ca`).
+#
+# These are lightweight CPU-only pods (no GPU), so they are NOT pinned to the
+# NUCBox via nodeSelector — k3s can schedule them on any amd64 node. Models are
+# cached in a local-path PVC (`/data`) so they survive pod restarts without
+# re-downloading.
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: wyoming-whisper-data
+  namespace: llamacpp
+  labels:
+    app: llamacpp
+    component: stt
+spec:
+  storageClassName: local-path
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: 5Gi
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: wyoming-whisper
+  namespace: llamacpp
+  labels:
+    app: llamacpp
+    component: stt
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate
+  selector:
+    matchLabels:
+      app: llamacpp
+      component: stt
+  template:
+    metadata:
+      labels:
+        app: llamacpp
+        component: stt
+    spec:
+      nodeSelector:
+        kubernetes.io/arch: amd64
+      containers:
+      - name: wyoming-whisper
+        image: rhasspy/wyoming-whisper
+        imagePullPolicy: IfNotPresent
+        args:
+        - --uri
+        - tcp://0.0.0.0:10300
+        - --language      # pin transcription language to Catalan
+        - ca
+        - --model         # faster-whisper model (tune up to medium for accuracy)
+        - small
+        ports:
+        - name: wyoming
+          containerPort: 10300
+        resources:
+          requests:
+            cpu: "100m"
+            memory: "256Mi"
+          limits:
+            cpu: "1000m"
+            memory: "1Gi"
+        volumeMounts:
+        - name: data
+          mountPath: /data
+      volumes:
+      - name: data
+        persistentVolumeClaim:
+          claimName: wyoming-whisper-data
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: wyoming-whisper
+  namespace: llamacpp
+  labels:
+    app: llamacpp
+    component: stt
+spec:
+  type: ClusterIP
+  selector:
+    app: llamacpp
+    component: stt
+  ports:
+  - name: wyoming
+    port: 10300
+    targetPort: 10300
diff --git a/llamacpp/deployment-tts.yaml b/llamacpp/deployment-tts.yaml
new file mode 100644
index 0000000..1bc18e8
--- /dev/null
+++ b/llamacpp/deployment-tts.yaml
@@ -0,0 +1,93 @@
+# Wyoming Text-to-Speech (rhasspy/wyoming-piper).
+#
+# Exposes the Wyoming protocol over TCP on port 10200 so Home Assistant's
+# Wyoming TTS integration can send text and receive synthesized audio. Uses
+# Piper under the hood with the Catalan voice `ca_ES-upc_ona-medium`.
+#
+# Lightweight CPU-only pod (no GPU), not pinned to the NUCBox. The voice is
+# cached in a local-path PVC (`/data`) so it survives pod restarts.
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: wyoming-piper-data
+  namespace: llamacpp
+  labels:
+    app: llamacpp
+    component: tts
+spec:
+  storageClassName: local-path
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: 1Gi
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: wyoming-piper
+  namespace: llamacpp
+  labels:
+    app: llamacpp
+    component: tts
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate
+  selector:
+    matchLabels:
+      app: llamacpp
+      component: tts
+  template:
+    metadata:
+      labels:
+        app: llamacpp
+        component: tts
+    spec:
+      nodeSelector:
+        kubernetes.io/arch: amd64
+      containers:
+      - name: wyoming-piper
+        image: rhasspy/wyoming-piper
+        imagePullPolicy: IfNotPresent
+        args:
+        - --uri
+        - tcp://0.0.0.0:10200
+        - --voice         # Catalan (Spain) medium-quality UPC Ona voice
+        - ca_ES-upc_ona-medium
+        ports:
+        - name: wyoming
+          containerPort: 10200
+        resources:
+          requests:
+            cpu: "100m"
+            memory: "128Mi"
+          limits:
+            cpu: "500m"
+            memory: "512Mi"
+        volumeMounts:
+        - name: data
+          mountPath: /data
+      volumes:
+      - name: data
+        persistentVolumeClaim:
+          claimName: wyoming-piper-data
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: wyoming-piper
+  namespace: llamacpp
+  labels:
+    app: llamacpp
+    component: tts
+spec:
+  type: ClusterIP
+  selector:
+    app: llamacpp
+    component: tts
+  ports:
+  - name: wyoming
+    port: 10200
+    targetPort: 10200