gx10/tts: persist Piper /tts source + manifest (telephony TTS port baseline)

Dockerfile (linux/arm64, en_US-amy-medium baked), tts_service.py (16kHz/16-bit/mono
WAV, numpy resample 22050->16000), gx10-tts.yaml (CPU NodePort 30850, no GPU request),
README (build/import/cutover/verify on the GX10 cluster).
This commit is contained in:
Andrew Stoltz
2026-06-14 14:14:59 -05:00
parent e4d1735d35
commit d03a92407d
4 changed files with 324 additions and 0 deletions

81
gx10/tts/gx10-tts.yaml Normal file
View File

@@ -0,0 +1,81 @@
# GX10 Piper TTS — telephony /tts endpoint on the GX10 RKE2 cluster.
# Applied DIRECTLY via the GX10's own kubectl (KUBECONFIG=/etc/rancher/rke2/rke2.yaml);
# the GX10 cluster is NOT yet under the old-cluster ArgoCD. CPU-only (no GPU request)
# so it co-resides with the GPU-holding Ollama pod without contending for the GB10.
# Image is imported into RKE2 containerd (imagePullPolicy: Never).
# Telephony reaches it at http://10.0.56.14:30850 (NodePort, MGMT VLAN 56).
apiVersion: v1
kind: Namespace
metadata:
name: tts
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: gx10-tts
namespace: tts
labels:
app: gx10-tts
spec:
replicas: 1
selector:
matchLabels:
app: gx10-tts
template:
metadata:
labels:
app: gx10-tts
spec:
containers:
- name: tts
image: localhost/fc-gx10-tts:v20260614
imagePullPolicy: Never
ports:
- containerPort: 8500
name: http
env:
- name: TTS_PORT
value: "8500"
- name: PIPER_VOICE
value: "en_US-amy-medium"
- name: TARGET_RATE
value: "16000"
readinessProbe:
httpGet:
path: /health
port: 8500
initialDelaySeconds: 3
periodSeconds: 5
timeoutSeconds: 3
livenessProbe:
httpGet:
path: /health
port: 8500
initialDelaySeconds: 10
periodSeconds: 20
timeoutSeconds: 5
resources:
requests:
cpu: "500m"
memory: "512Mi"
limits:
cpu: "4"
memory: "2Gi"
---
apiVersion: v1
kind: Service
metadata:
name: gx10-tts
namespace: tts
labels:
app: gx10-tts
spec:
type: NodePort
selector:
app: gx10-tts
ports:
- name: http
port: 8500
targetPort: 8500
nodePort: 30850
protocol: TCP