diff --git a/AudioQnA/kubernetes/manifests/README.md b/AudioQnA/kubernetes/manifests/README.md
new file mode 100644
index 000000000..ab1ce2cbc
--- /dev/null
+++ b/AudioQnA/kubernetes/manifests/README.md
@@ -0,0 +1,32 @@
+# Deploy VisualQnA in a Kubernetes Cluster
+
+> [NOTE]
+> The following values must be set before you can deploy:
+> HUGGINGFACEHUB_API_TOKEN
+> You can also customize the "MODEL_ID" and "model-volume"
+
+## Deploy On Xeon
+```
+cd GenAIExamples/AudioQnA/kubernetes/manifests/xeon
+export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
+sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" audioqna.yaml
+kubectl apply -f audioqna.yaml
+```
+## Deploy On Gaudi
+```
+cd GenAIExamples/AudioQnA/kubernetes/manifests/gaudi
+export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
+sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" audioqna.yaml
+kubectl apply -f audioqna.yaml
+```
+
+
+## Verify Services
+
+Make sure all the pods are running, and restart the audioqna-xxxx pod if necessary.
+
+```bash
+kubectl get pods
+
+curl http://${host_ip}:3008/v1/audioqna   -X POST   -d '{"audio": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA", "max_tokens":64}'   -H 'Content-Type: application/json'
+```
diff --git a/AudioQnA/kubernetes/manifests/gaudi/audioqna.yaml b/AudioQnA/kubernetes/manifests/gaudi/audioqna.yaml
new file mode 100644
index 000000000..5a824ef3e
--- /dev/null
+++ b/AudioQnA/kubernetes/manifests/gaudi/audioqna.yaml
@@ -0,0 +1,439 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: audio-qna-config
+  namespace: default
+data:
+  ASR_ENDPOINT: http://whisper-svc.default.svc.cluster.local:7066
+  TTS_ENDPOINT: http://speecht5-svc.default.svc.cluster.local:7055
+  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
+  HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+  TGI_LLM_ENDPOINT: http://llm-dependency-svc.default.svc.cluster.local:3006
+  MEGA_SERVICE_HOST_IP: audioqna-backend-server-svc
+  ASR_SERVICE_HOST_IP: asr-svc
+  ASR_SERVICE_PORT: "3001"
+  LLM_SERVICE_HOST_IP: llm-svc
+  LLM_SERVICE_PORT: "3007"
+  TTS_SERVICE_HOST_IP: tts-svc
+  TTS_SERVICE_PORT: "3002"
+
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: asr-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: asr-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: asr-deploy
+    spec:
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: asr-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: audio-qna-config
+        image: opea/asr:latest
+        imagePullPolicy: IfNotPresent
+        name: asr-deploy
+        args: null
+        ports:
+        - containerPort: 9099
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: asr-svc
+spec:
+  type: ClusterIP
+  selector:
+    app: asr-deploy
+  ports:
+  - name: service
+    port: 3001
+    targetPort: 9099
+---
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: whisper-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: whisper-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: whisper-deploy
+    spec:
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: whisper-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: audio-qna-config
+        image: opea/whisper-gaudi:latest
+        imagePullPolicy: IfNotPresent
+        name: whisper-deploy
+        args: null
+        ports:
+        - containerPort: 7066
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        env:
+        - name: OMPI_MCA_btl_vader_single_copy_mechanism
+          value: none
+        - name: PT_HPU_ENABLE_LAZY_COLLECTIVES
+          value: 'true'
+        - name: runtime
+          value: habana
+        - name: HABANA_VISIBLE_DEVICES
+          value: all
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: whisper-svc
+spec:
+  type: ClusterIP
+  selector:
+    app: whisper-deploy
+  ports:
+  - name: service
+    port: 7066
+    targetPort: 7066
+
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: tts-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: tts-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: tts-deploy
+    spec:
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: tts-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: audio-qna-config
+        image: opea/tts:latest
+        imagePullPolicy: IfNotPresent
+        name: tts-deploy
+        args: null
+        ports:
+        - containerPort: 9088
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: tts-svc
+spec:
+  type: ClusterIP
+  selector:
+    app: tts-deploy
+  ports:
+  - name: service
+    port: 3002
+    targetPort: 9088
+
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: speecht5-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: speecht5-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: speecht5-deploy
+    spec:
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: speecht5-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: audio-qna-config
+        image: opea/speecht5-gaudi:latest
+        imagePullPolicy: IfNotPresent
+        name: speecht5-deploy
+        args: null
+        ports:
+        - containerPort: 7055
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        env:
+        - name: OMPI_MCA_btl_vader_single_copy_mechanism
+          value: none
+        - name: PT_HPU_ENABLE_LAZY_COLLECTIVES
+          value: 'true'
+        - name: runtime
+          value: habana
+        - name: HABANA_VISIBLE_DEVICES
+          value: all
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: speecht5-svc
+spec:
+  type: ClusterIP
+  selector:
+    app: speecht5-deploy
+  ports:
+  - name: service
+    port: 7055
+    targetPort: 7055
+
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-dependency-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: llm-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-dependency-deploy
+    spec:
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: audio-qna-config
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.1
+        name: llm-dependency-deploy-demo
+        securityContext:
+          capabilities:
+            add:
+            - SYS_NICE
+        args:
+        - --model-id
+        - $(LLM_MODEL_ID)
+        - --max-input-length
+        - '2048'
+        - --max-total-tokens
+        - '4096'
+        - --max-batch-total-tokens
+        - '65536'
+        - --max-batch-prefill-tokens
+        - '4096'
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        env:
+        - name: OMPI_MCA_btl_vader_single_copy_mechanism
+          value: none
+        - name: PT_HPU_ENABLE_LAZY_COLLECTIVES
+          value: 'true'
+        - name: runtime
+          value: habana
+        - name: HABANA_VISIBLE_DEVICES
+          value: all
+        - name: PREFILL_BATCH_BUCKET_SIZE
+          value: "1"
+        - name: BATCH_BUCKET_SIZE
+          value: "8"
+      serviceAccountName: default
+      volumes:
+      - name: model-volume
+        hostPath:
+          path: /home/sdp/cesg
+          type: Directory
+      - name: shm
+        emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: llm-dependency-svc
+spec:
+  type: ClusterIP
+  selector:
+    app: llm-dependency-deploy
+  ports:
+  - name: service
+    port: 3006
+    targetPort: 80
+
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: llm-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-deploy
+    spec:
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: llm-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: audio-qna-config
+        image: opea/llm-tgi:latest
+        imagePullPolicy: IfNotPresent
+        name: llm-deploy
+        args: null
+        ports:
+        - containerPort: 9000
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: llm-svc
+spec:
+  type: ClusterIP
+  selector:
+    app: llm-deploy
+  ports:
+  - name: service
+    port: 3007
+    targetPort: 9000
+
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: audioqna-backend-server-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: audioqna-backend-server-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: audioqna-backend-server-deploy
+    spec:
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: audioqna-backend-server-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: audio-qna-config
+        image: opea/audioqna:latest
+        imagePullPolicy: IfNotPresent
+        name: audioqna-backend-server-deploy
+        args: null
+        ports:
+        - containerPort: 8888
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: audioqna-backend-server-svc
+spec:
+  type: NodePort
+  selector:
+    app: audioqna-backend-server-deploy
+  ports:
+  - name: service
+    port: 3008
+    targetPort: 8888
+    nodePort: 30666
diff --git a/AudioQnA/kubernetes/manifests/xeon/audioqna.yaml b/AudioQnA/kubernetes/manifests/xeon/audioqna.yaml
new file mode 100644
index 000000000..89b3e6b1a
--- /dev/null
+++ b/AudioQnA/kubernetes/manifests/xeon/audioqna.yaml
@@ -0,0 +1,395 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: audio-qna-config
+  namespace: default
+data:
+  ASR_ENDPOINT: http://whisper-svc.default.svc.cluster.local:7066
+  TTS_ENDPOINT: http://speecht5-svc.default.svc.cluster.local:7055
+  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
+  HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+  TGI_LLM_ENDPOINT: http://llm-dependency-svc.default.svc.cluster.local:3006
+  MEGA_SERVICE_HOST_IP: audioqna-backend-server-svc
+  ASR_SERVICE_HOST_IP: asr-svc
+  ASR_SERVICE_PORT: "3001"
+  LLM_SERVICE_HOST_IP: llm-svc
+  LLM_SERVICE_PORT: "3007"
+  TTS_SERVICE_HOST_IP: tts-svc
+  TTS_SERVICE_PORT: "3002"
+
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: asr-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: asr-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: asr-deploy
+    spec:
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: asr-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: audio-qna-config
+        image: opea/asr:latest
+        imagePullPolicy: IfNotPresent
+        name: asr-deploy
+        args: null
+        ports:
+        - containerPort: 9099
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: asr-svc
+spec:
+  type: ClusterIP
+  selector:
+    app: asr-deploy
+  ports:
+  - name: service
+    port: 3001
+    targetPort: 9099
+---
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: whisper-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: whisper-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: whisper-deploy
+    spec:
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: whisper-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: audio-qna-config
+        image: opea/whisper:latest
+        imagePullPolicy: IfNotPresent
+        name: whisper-deploy
+        args: null
+        ports:
+        - containerPort: 7066
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: whisper-svc
+spec:
+  type: ClusterIP
+  selector:
+    app: whisper-deploy
+  ports:
+  - name: service
+    port: 7066
+    targetPort: 7066
+
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: tts-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: tts-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: tts-deploy
+    spec:
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: tts-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: audio-qna-config
+        image: opea/tts:latest
+        imagePullPolicy: IfNotPresent
+        name: tts-deploy
+        args: null
+        ports:
+        - containerPort: 9088
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: tts-svc
+spec:
+  type: ClusterIP
+  selector:
+    app: tts-deploy
+  ports:
+  - name: service
+    port: 3002
+    targetPort: 9088
+
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: speecht5-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: speecht5-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: speecht5-deploy
+    spec:
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: speecht5-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: audio-qna-config
+        image: opea/speecht5:latest
+        imagePullPolicy: IfNotPresent
+        name: speecht5-deploy
+        args: null
+        ports:
+        - containerPort: 7055
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: speecht5-svc
+spec:
+  type: ClusterIP
+  selector:
+    app: speecht5-deploy
+  ports:
+  - name: service
+    port: 7055
+    targetPort: 7055
+
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-dependency-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: llm-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-dependency-deploy
+    spec:
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: audio-qna-config
+        image: ghcr.io/huggingface/text-generation-inference:2.2.0
+        name: llm-dependency-deploy-demo
+        securityContext:
+          capabilities:
+            add:
+            - SYS_NICE
+        args:
+        - --model-id
+        - $(LLM_MODEL_ID)
+        - --max-input-length
+        - '2048'
+        - --max-total-tokens
+        - '4096'
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+        ports:
+        - containerPort: 80
+      serviceAccountName: default
+      volumes:
+      - name: model-volume
+        hostPath:
+          path: /home/sdp/cesg
+          type: Directory
+      - name: shm
+        emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: llm-dependency-svc
+spec:
+  type: ClusterIP
+  selector:
+    app: llm-dependency-deploy
+  ports:
+  - name: service
+    port: 3006
+    targetPort: 80
+
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: llm-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-deploy
+    spec:
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: llm-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: audio-qna-config
+        image: opea/llm-tgi:latest
+        imagePullPolicy: IfNotPresent
+        name: llm-deploy
+        args: null
+        ports:
+        - containerPort: 9000
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: llm-svc
+spec:
+  type: ClusterIP
+  selector:
+    app: llm-deploy
+  ports:
+  - name: service
+    port: 3007
+    targetPort: 9000
+
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: audioqna-backend-server-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: audioqna-backend-server-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: audioqna-backend-server-deploy
+    spec:
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: audioqna-backend-server-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: audio-qna-config
+        image: opea/audioqna:latest
+        imagePullPolicy: IfNotPresent
+        name: audioqna-backend-server-deploy
+        args: null
+        ports:
+        - containerPort: 8888
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: audioqna-backend-server-svc
+spec:
+  type: NodePort
+  selector:
+    app: audioqna-backend-server-deploy
+  ports:
+  - name: service
+    port: 3008
+    targetPort: 8888
+    nodePort: 30666