From 3a551eceb7e0ca2a1e4a36a93fd07206c37a7524 Mon Sep 17 00:00:00 2001
From: rootflo-hardik <hardik@rootflo.ai>
Date: Fri, 20 Mar 2026 11:49:52 +0530
Subject: [PATCH 1/2] feat(voice_agent): add Azure TTS and STT provider support

---
 .../client/src/config/voice-providers.ts      | 83 ++++++++++++++++++-
 .../stt-configs/CreateSttConfigDialog.tsx     | 41 +++++++--
 .../stt-configs/EditSttConfigDialog.tsx       | 29 ++++++-
 .../tts-configs/CreateTtsConfigDialog.tsx     | 43 ++++++++--
 .../tts-configs/EditTtsConfigDialog.tsx       | 29 ++++++-
 wavefront/client/src/types/stt-config.ts      | 11 ++-
 wavefront/client/src/types/tts-config.ts      | 13 ++-
 .../services/pipecat_service.py               |  2 +
 .../call_processing/services/stt_service.py   | 42 +++++++++-
 .../call_processing/services/tts_service.py   | 71 +++++++++++++++-
 ...3b06cfe7f_add_region_to_tts_stt_configs.py | 33 ++++++++
 .../db_repo_module/models/stt_config.py       |  1 +
 .../db_repo_module/models/tts_config.py       |  1 +
 .../controllers/stt_config_controller.py      |  3 +
 .../controllers/tts_config_controller.py      |  3 +
 .../voice_agents_module/models/stt_schemas.py |  5 ++
 .../voice_agents_module/models/tts_schemas.py |  5 ++
 .../services/stt_config_service.py            |  3 +
 .../services/tts_config_service.py            |  3 +
 19 files changed, 396 insertions(+), 25 deletions(-)
 create mode 100644 wavefront/server/modules/db_repo_module/db_repo_module/alembic/versions/2026_03_19_1716-c153b06cfe7f_add_region_to_tts_stt_configs.py

diff --git a/wavefront/client/src/config/voice-providers.ts b/wavefront/client/src/config/voice-providers.ts
index 66592821..6c679b17 100644
--- a/wavefront/client/src/config/voice-providers.ts
+++ b/wavefront/client/src/config/voice-providers.ts
@@ -44,7 +44,7 @@ export interface VoiceProvidersConfig {
  */
 export const VOICE_PROVIDERS_CONFIG: VoiceProvidersConfig = {
   tts: {
-    providers: ['elevenlabs', 'deepgram', 'cartesia', 'sarvam'] as const,
+    providers: ['elevenlabs', 'deepgram', 'cartesia', 'sarvam', 'azure'] as const,
     configs: {
       elevenlabs: {
         name: 'ElevenLabs',
@@ -217,10 +217,61 @@ export const VOICE_PROVIDERS_CONFIG: VoiceProvidersConfig = {
           },
         },
       },
+      azure: {
+        name: 'Azure',
+        badge: {
+          bg: 'bg-sky-100',
+          text: 'text-sky-700',
+        },
+        parameters: {
+          style: {
+            type: 'string' as const,
+            default: '',
+            description: 'Speaking style (e.g. cheerful, sad, angry)',
+            placeholder: 'cheerful',
+          },
+          rate: {
+            type: 'string' as const,
+            default: '',
+            description: 'Speech rate (e.g. +10%, fast, slow)',
+            placeholder: '+0%',
+          },
+          pitch: {
+            type: 'string' as const,
+            default: '',
+            description: 'Pitch adjustment (e.g. +0Hz, high, low)',
+            placeholder: '+0Hz',
+          },
+          role: {
+            type: 'string' as const,
+            default: '',
+            description: 'Voice role for expression (e.g. YoungAdultFemale)',
+            placeholder: 'YoungAdultFemale',
+          },
+          style_degree: {
+            type: 'string' as const,
+            default: '',
+            description: 'Intensity of speaking style (0.01 to 2.0)',
+            placeholder: '1.0',
+          },
+          volume: {
+            type: 'string' as const,
+            default: '',
+            description: 'Volume level (e.g. +20%, loud, x-soft)',
+            placeholder: '+0%',
+          },
+          sample_rate: {
+            type: 'number' as const,
+            default: undefined,
+            description: 'Audio sample rate in Hz',
+            placeholder: '16000',
+          },
+        },
+      },
     },
   },
   stt: {
-    providers: ['deepgram', 'sarvam', 'elevenlabs'] as const,
+    providers: ['deepgram', 'sarvam', 'elevenlabs', 'azure'] as const,
     configs: {
       deepgram: {
         name: 'Deepgram',
@@ -352,6 +403,34 @@ export const VOICE_PROVIDERS_CONFIG: VoiceProvidersConfig = {
           },
         },
       },
+      azure: {
+        name: 'Azure',
+        badge: {
+          bg: 'bg-sky-100',
+          text: 'text-sky-700',
+        },
+        parameters: {
+          endpoint_id: {
+            type: 'string' as const,
+            default: '',
+            description: 'Custom model endpoint ID (optional)',
+            placeholder: '',
+          },
+          sample_rate: {
+            type: 'number' as const,
+            default: undefined,
+            description: 'Audio sample rate in Hz',
+            placeholder: '8000',
+          },
+          ttfs_p99_latency: {
+            type: 'number' as const,
+            default: undefined,
+            description: 'P99 latency threshold in seconds for first speech detection',
+            placeholder: '1.5',
+            step: 0.1,
+          },
+        },
+      },
     },
   },
 };
diff --git a/wavefront/client/src/pages/apps/[appId]/voice-agents/stt-configs/CreateSttConfigDialog.tsx b/wavefront/client/src/pages/apps/[appId]/voice-agents/stt-configs/CreateSttConfigDialog.tsx
index dd9e48c9..c147fd44 100644
--- a/wavefront/client/src/pages/apps/[appId]/voice-agents/stt-configs/CreateSttConfigDialog.tsx
+++ b/wavefront/client/src/pages/apps/[appId]/voice-agents/stt-configs/CreateSttConfigDialog.tsx
@@ -30,12 +30,18 @@ import React, { useEffect, useState } from 'react';
 import { useForm } from 'react-hook-form';
 import { z } from 'zod';
 
-const createSttConfigSchema = z.object({
-  display_name: z.string().min(1, 'Display name is required').max(100, 'Display name must be 100 characters or less'),
-  description: z.string().max(500, 'Description must be 500 characters or less').optional(),
-  provider: z.enum(['deepgram', 'sarvam', 'elevenlabs'] as [string, ...string[]]),
-  api_key: z.string().min(1, 'API key is required'),
-});
+const createSttConfigSchema = z
+  .object({
+    display_name: z.string().min(1, 'Display name is required').max(100, 'Display name must be 100 characters or less'),
+    description: z.string().max(500, 'Description must be 500 characters or less').optional(),
+    provider: z.enum(['deepgram', 'sarvam', 'elevenlabs', 'azure'] as [string, ...string[]]),
+    api_key: z.string().min(1, 'API key is required'),
+    region: z.string().optional(),
+  })
+  .refine((data) => data.provider !== 'azure' || (data.region && data.region.trim().length > 0), {
+    message: 'Region is required for Azure',
+    path: ['region'],
+  });
 
 type CreateSttConfigInput = z.infer<typeof createSttConfigSchema>;
 
@@ -56,9 +62,12 @@ const CreateSttConfigDialog: React.FC<CreateSttConfigDialogProps> = ({ isOpen, o
       description: '',
       provider: 'deepgram',
       api_key: '',
+      region: '',
     },
   });
 
+  const selectedProvider = form.watch('provider');
+
   // Reset form when dialog closes
   useEffect(() => {
     if (!isOpen) {
@@ -67,6 +76,7 @@ const CreateSttConfigDialog: React.FC<CreateSttConfigDialogProps> = ({ isOpen, o
         description: '',
         provider: 'deepgram',
         api_key: '',
+        region: '',
       });
     }
   }, [isOpen, form]);
@@ -79,6 +89,7 @@ const CreateSttConfigDialog: React.FC<CreateSttConfigDialogProps> = ({ isOpen, o
         description: data.description?.trim() || null,
         provider: data.provider as SttProvider,
         api_key: data.api_key.trim(),
+        region: data.region?.trim() || null,
       });
       notifySuccess('STT configuration created successfully');
       onSuccess?.();
@@ -186,6 +197,24 @@ const CreateSttConfigDialog: React.FC<CreateSttConfigDialogProps> = ({ isOpen, o
               )}
             />
 
+            {selectedProvider === 'azure' && (
+              <FormField
+                control={form.control}
+                name="region"
+                render={({ field }) => (
+                  <FormItem>
+                    <FormLabel>
+                      Region <span className="text-red-500">*</span>
+                    </FormLabel>
+                    <FormControl>
+                      <Input placeholder="e.g., eastus, westus2" {...field} />
+                    </FormControl>
+                    <FormMessage />
+                  </FormItem>
+                )}
+              />
+            )}
+
             <Alert variant="info">
               <AlertDescription>
                 <strong>Security Note:</strong> API keys are stored securely and never returned in API responses.
diff --git a/wavefront/client/src/pages/apps/[appId]/voice-agents/stt-configs/EditSttConfigDialog.tsx b/wavefront/client/src/pages/apps/[appId]/voice-agents/stt-configs/EditSttConfigDialog.tsx
index 8213a558..c4eabf5a 100644
--- a/wavefront/client/src/pages/apps/[appId]/voice-agents/stt-configs/EditSttConfigDialog.tsx
+++ b/wavefront/client/src/pages/apps/[appId]/voice-agents/stt-configs/EditSttConfigDialog.tsx
@@ -33,8 +33,9 @@ import { z } from 'zod';
 const updateSttConfigSchema = z.object({
   display_name: z.string().min(1, 'Display name is required').max(100, 'Display name must be 100 characters or less'),
   description: z.string().max(500, 'Description must be 500 characters or less').optional(),
-  provider: z.enum(['deepgram', 'sarvam', 'elevenlabs'] as [string, ...string[]]),
+  provider: z.enum(['deepgram', 'sarvam', 'elevenlabs', 'azure'] as [string, ...string[]]),
   api_key: z.string().optional(),
+  region: z.string().optional(),
 });
 
 type UpdateSttConfigInput = z.infer<typeof updateSttConfigSchema>;
@@ -57,9 +58,12 @@ const EditSttConfigDialog: React.FC<EditSttConfigDialogProps> = ({ isOpen, onOpe
       description: config.description || '',
       provider: config.provider,
       api_key: '',
+      region: config.region || '',
     },
   });
 
+  const selectedProvider = form.watch('provider');
+
   // Reset form when dialog opens or config changes
   useEffect(() => {
     if (isOpen && config) {
@@ -68,6 +72,7 @@ const EditSttConfigDialog: React.FC<EditSttConfigDialogProps> = ({ isOpen, onOpe
         description: config.description || '',
         provider: config.provider,
         api_key: '',
+        region: config.region || '',
       });
     }
   }, [isOpen, config, form]);
@@ -84,6 +89,10 @@ const EditSttConfigDialog: React.FC<EditSttConfigDialogProps> = ({ isOpen, onOpe
         updateData.api_key = data.api_key.trim();
       }
 
+      if (data.region !== undefined) {
+        updateData.region = data.region?.trim() || null;
+      }
+
       await floConsoleService.sttConfigService.updateSttConfig(config.id, updateData);
       notifySuccess('STT configuration updated successfully');
       onSuccess?.();
@@ -196,6 +205,24 @@ const EditSttConfigDialog: React.FC<EditSttConfigDialogProps> = ({ isOpen, onOpe
               )}
             />
 
+            {selectedProvider === 'azure' && (
+              <FormField
+                control={form.control}
+                name="region"
+                render={({ field }) => (
+                  <FormItem>
+                    <FormLabel>
+                      Region <span className="text-red-500">*</span>
+                    </FormLabel>
+                    <FormControl>
+                      <Input placeholder="e.g., eastus, westus2" {...field} />
+                    </FormControl>
+                    <FormMessage />
+                  </FormItem>
+                )}
+              />
+            )}
+
             <DialogFooter>
               <Button type="button" variant="outline" onClick={() => onOpenChange(false)} disabled={loading}>
                 Cancel
diff --git a/wavefront/client/src/pages/apps/[appId]/voice-agents/tts-configs/CreateTtsConfigDialog.tsx b/wavefront/client/src/pages/apps/[appId]/voice-agents/tts-configs/CreateTtsConfigDialog.tsx
index 77d3fad0..2586493a 100644
--- a/wavefront/client/src/pages/apps/[appId]/voice-agents/tts-configs/CreateTtsConfigDialog.tsx
+++ b/wavefront/client/src/pages/apps/[appId]/voice-agents/tts-configs/CreateTtsConfigDialog.tsx
@@ -29,12 +29,18 @@ import React, { useEffect, useState } from 'react';
 import { useForm } from 'react-hook-form';
 import { z } from 'zod';
 
-const createTtsConfigSchema = z.object({
-  display_name: z.string().min(1, 'Display name is required').max(100, 'Display name must be 100 characters or less'),
-  description: z.string().max(500, 'Description must be 500 characters or less').optional(),
-  provider: z.enum(['elevenlabs', 'deepgram', 'cartesia', 'sarvam'] as [string, ...string[]]),
-  api_key: z.string().min(1, 'API key is required'),
-});
+const createTtsConfigSchema = z
+  .object({
+    display_name: z.string().min(1, 'Display name is required').max(100, 'Display name must be 100 characters or less'),
+    description: z.string().max(500, 'Description must be 500 characters or less').optional(),
+    provider: z.enum(['elevenlabs', 'deepgram', 'cartesia', 'sarvam', 'azure'] as [string, ...string[]]),
+    api_key: z.string().min(1, 'API key is required'),
+    region: z.string().optional(),
+  })
+  .refine((data) => data.provider !== 'azure' || (data.region && data.region.trim().length > 0), {
+    message: 'Region is required for Azure',
+    path: ['region'],
+  });
 
 type CreateTtsConfigInput = z.infer<typeof createTtsConfigSchema>;
 
@@ -55,9 +61,12 @@ const CreateTtsConfigDialog: React.FC<CreateTtsConfigDialogProps> = ({ isOpen, o
       description: '',
       provider: 'elevenlabs',
       api_key: '',
+      region: '',
     },
   });
 
+  const selectedProvider = form.watch('provider');
+
   // Reset form when dialog closes
   useEffect(() => {
     if (!isOpen) {
@@ -66,6 +75,7 @@ const CreateTtsConfigDialog: React.FC<CreateTtsConfigDialogProps> = ({ isOpen, o
         description: '',
         provider: 'elevenlabs',
         api_key: '',
+        region: '',
       });
     }
   }, [isOpen, form]);
@@ -76,8 +86,9 @@ const CreateTtsConfigDialog: React.FC<CreateTtsConfigDialogProps> = ({ isOpen, o
       await floConsoleService.ttsConfigService.createTtsConfig({
         display_name: data.display_name.trim(),
         description: data.description?.trim() || null,
-        provider: data.provider as 'elevenlabs' | 'deepgram' | 'cartesia',
+        provider: data.provider as 'elevenlabs' | 'deepgram' | 'cartesia' | 'sarvam' | 'azure',
         api_key: data.api_key.trim(),
+        region: data.region?.trim() || null,
       });
       notifySuccess('TTS configuration created successfully');
       onSuccess?.();
@@ -185,6 +196,24 @@ const CreateTtsConfigDialog: React.FC<CreateTtsConfigDialogProps> = ({ isOpen, o
               )}
             />
 
+            {selectedProvider === 'azure' && (
+              <FormField
+                control={form.control}
+                name="region"
+                render={({ field }) => (
+                  <FormItem>
+                    <FormLabel>
+                      Region <span className="text-red-500">*</span>
+                    </FormLabel>
+                    <FormControl>
+                      <Input placeholder="e.g., eastus, westus2" {...field} />
+                    </FormControl>
+                    <FormMessage />
+                  </FormItem>
+                )}
+              />
+            )}
+
             <Alert variant="info">
               <AlertDescription>
                 <strong>Security Note:</strong> API keys are stored securely and never returned in API responses.
diff --git a/wavefront/client/src/pages/apps/[appId]/voice-agents/tts-configs/EditTtsConfigDialog.tsx b/wavefront/client/src/pages/apps/[appId]/voice-agents/tts-configs/EditTtsConfigDialog.tsx
index dc6df2e1..ef668f29 100644
--- a/wavefront/client/src/pages/apps/[appId]/voice-agents/tts-configs/EditTtsConfigDialog.tsx
+++ b/wavefront/client/src/pages/apps/[appId]/voice-agents/tts-configs/EditTtsConfigDialog.tsx
@@ -33,8 +33,9 @@ import { z } from 'zod';
 const updateTtsConfigSchema = z.object({
   display_name: z.string().min(1, 'Display name is required').max(100, 'Display name must be 100 characters or less'),
   description: z.string().max(500, 'Description must be 500 characters or less').optional(),
-  provider: z.enum(['elevenlabs', 'deepgram', 'cartesia', 'sarvam'] as [string, ...string[]]),
+  provider: z.enum(['elevenlabs', 'deepgram', 'cartesia', 'sarvam', 'azure'] as [string, ...string[]]),
   api_key: z.string().optional(),
+  region: z.string().optional(),
 });
 
 type UpdateTtsConfigInput = z.infer<typeof updateTtsConfigSchema>;
@@ -57,9 +58,12 @@ const EditTtsConfigDialog: React.FC<EditTtsConfigDialogProps> = ({ isOpen, onOpe
       description: config.description || '',
       provider: config.provider,
       api_key: '',
+      region: config.region || '',
     },
   });
 
+  const selectedProvider = form.watch('provider');
+
   // Reset form when dialog opens or config changes
   useEffect(() => {
     if (isOpen && config) {
@@ -68,6 +72,7 @@ const EditTtsConfigDialog: React.FC<EditTtsConfigDialogProps> = ({ isOpen, onOpe
         description: config.description || '',
         provider: config.provider,
         api_key: '',
+        region: config.region || '',
       });
     }
   }, [isOpen, config, form]);
@@ -84,6 +89,10 @@ const EditTtsConfigDialog: React.FC<EditTtsConfigDialogProps> = ({ isOpen, onOpe
         updateData.api_key = data.api_key.trim();
       }
 
+      if (data.region !== undefined) {
+        updateData.region = data.region?.trim() || null;
+      }
+
       await floConsoleService.ttsConfigService.updateTtsConfig(config.id, updateData);
       notifySuccess('TTS configuration updated successfully');
       onSuccess?.();
@@ -196,6 +205,24 @@ const EditTtsConfigDialog: React.FC<EditTtsConfigDialogProps> = ({ isOpen, onOpe
               )}
             />
 
+            {selectedProvider === 'azure' && (
+              <FormField
+                control={form.control}
+                name="region"
+                render={({ field }) => (
+                  <FormItem>
+                    <FormLabel>
+                      Region <span className="text-red-500">*</span>
+                    </FormLabel>
+                    <FormControl>
+                      <Input placeholder="e.g., eastus, westus2" {...field} />
+                    </FormControl>
+                    <FormMessage />
+                  </FormItem>
+                )}
+              />
+            )}
+
             <DialogFooter>
               <Button type="button" variant="outline" onClick={() => onOpenChange(false)} disabled={loading}>
                 Cancel
diff --git a/wavefront/client/src/types/stt-config.ts b/wavefront/client/src/types/stt-config.ts
index 4f197840..25e12e13 100644
--- a/wavefront/client/src/types/stt-config.ts
+++ b/wavefront/client/src/types/stt-config.ts
@@ -1,12 +1,13 @@
 import { IApiResponse } from '@app/lib/axios';
 
-export type SttProvider = 'deepgram' | 'sarvam' | 'elevenlabs';
+export type SttProvider = 'deepgram' | 'sarvam' | 'elevenlabs' | 'azure';
 
 export interface SttConfig {
   id: string;
   display_name: string;
   description: string | null;
   provider: SttProvider;
+  region: string | null;
   is_deleted: boolean;
   created_at: string;
   updated_at: string;
@@ -17,12 +18,14 @@ export interface CreateSttConfigRequest {
   description?: string | null;
   provider: SttProvider;
   api_key: string;
+  region?: string | null;
 }
 
 export interface UpdateSttConfigRequest {
   display_name?: string;
   description?: string | null;
   api_key?: string;
+  region?: string | null;
 }
 
 export interface SttConfigData {
@@ -67,3 +70,9 @@ export interface ElevenLabsSttParameters {
   language?: string; // ISO-639-1 code e.g. 'en', 'hi'
   sample_rate?: number; // default: 8000
 }
+
+// Azure STT specific parameters
+export interface AzureSttParameters {
+  endpoint_id?: string; // custom model endpoint ID
+  sample_rate?: number;
+}
diff --git a/wavefront/client/src/types/tts-config.ts b/wavefront/client/src/types/tts-config.ts
index bef161b4..10c6ac18 100644
--- a/wavefront/client/src/types/tts-config.ts
+++ b/wavefront/client/src/types/tts-config.ts
@@ -1,12 +1,13 @@
 import { IApiResponse } from '@app/lib/axios';
 
-export type TtsProvider = 'elevenlabs' | 'deepgram' | 'cartesia' | 'sarvam';
+export type TtsProvider = 'elevenlabs' | 'deepgram' | 'cartesia' | 'sarvam' | 'azure';
 
 export interface TtsConfig {
   id: string;
   display_name: string;
   description: string | null;
   provider: TtsProvider;
+  region: string | null;
   is_deleted: boolean;
   created_at: string;
   updated_at: string;
@@ -17,12 +18,14 @@ export interface CreateTtsConfigRequest {
   description?: string | null;
   provider: TtsProvider;
   api_key: string;
+  region?: string | null;
 }
 
 export interface UpdateTtsConfigRequest {
   display_name?: string;
   description?: string | null;
   api_key?: string;
+  region?: string | null;
 }
 
 export interface TtsConfigData {
@@ -73,3 +76,11 @@ export interface SarvamTtsParameters {
   enable_preprocessing?: boolean;
   temperature?: number; // 0.01 to 1.0
 }
+
+// Azure TTS specific parameters
+export interface AzureTtsParameters {
+  style?: string; // e.g. 'cheerful', 'sad', 'angry'
+  rate?: string; // e.g. '+10%', 'fast', 'slow'
+  pitch?: string; // e.g. '+0Hz', 'high', 'low'
+  sample_rate?: number;
+}
diff --git a/wavefront/server/apps/call_processing/call_processing/services/pipecat_service.py b/wavefront/server/apps/call_processing/call_processing/services/pipecat_service.py
index 477cc943..a6319f86 100644
--- a/wavefront/server/apps/call_processing/call_processing/services/pipecat_service.py
+++ b/wavefront/server/apps/call_processing/call_processing/services/pipecat_service.py
@@ -262,6 +262,7 @@ async def run_conversation(
         tts_config_with_params = {
             'provider': tts_config['provider'],
             'api_key': tts_config['api_key'],
+            'region': tts_config.get('region'),
             'voice_id': default_voice_id,  # Will be overridden per language in multi-lang mode
             'parameters': tts_parameters or {},
         }
@@ -270,6 +271,7 @@ async def run_conversation(
         stt_config_with_params = {
             'provider': stt_config['provider'],
             'api_key': stt_config['api_key'],
+            'region': stt_config.get('region'),
             'parameters': stt_parameters or {},
         }
 
diff --git a/wavefront/server/apps/call_processing/call_processing/services/stt_service.py b/wavefront/server/apps/call_processing/call_processing/services/stt_service.py
index e1d77623..e69b08a6 100644
--- a/wavefront/server/apps/call_processing/call_processing/services/stt_service.py
+++ b/wavefront/server/apps/call_processing/call_processing/services/stt_service.py
@@ -18,9 +18,7 @@
 # Deepgram options
 from deepgram import LiveOptions
 
-# Add more as needed:
-# from pipecat.services.assemblyai.stt import AssemblyAISTTService
-# from pipecat.services.whisper.stt import WhisperSTTService
+from pipecat.services.azure.stt import AzureSTTService
 
 
 class STTServiceFactory:
@@ -47,6 +45,7 @@ def create_stt_service(stt_config: Dict[str, Any]):
         """
         provider = stt_config['provider']
         api_key = stt_config['api_key']
+        region = stt_config.get('region')
         parameters = stt_config.get('parameters', {})
 
         if parameters is None:
@@ -60,6 +59,8 @@ def create_stt_service(stt_config: Dict[str, Any]):
             return STTServiceFactory._create_sarvam_stt(api_key, parameters)
         elif provider == 'elevenlabs':
             return STTServiceFactory._create_elevenlabs_stt(api_key, parameters)
+        elif provider == 'azure':
+            return STTServiceFactory._create_azure_stt(api_key, region, parameters)
         elif provider == 'assemblyai':
             return STTServiceFactory._create_assemblyai_stt(api_key, parameters)
         elif provider == 'whisper':
@@ -214,6 +215,41 @@ def _create_elevenlabs_stt(api_key: str, parameters: Dict[str, Any]):
             params=input_params,
         )
 
+    @staticmethod
+    def _create_azure_stt(api_key: str, region: str, parameters: Dict[str, Any]):
+        """Create Azure STT service"""
+        if not region:
+            raise ValueError("Azure STT requires 'region' to be set in the STT config")
+
+        kwargs = {
+            'api_key': api_key,
+            'region': region,
+        }
+
+        if 'sample_rate' in parameters and parameters['sample_rate']:
+            kwargs['sample_rate'] = parameters['sample_rate']
+        if 'endpoint_id' in parameters and parameters['endpoint_id']:
+            kwargs['endpoint_id'] = parameters['endpoint_id']
+        if (
+            'ttfs_p99_latency' in parameters
+            and parameters['ttfs_p99_latency'] is not None
+        ):
+            kwargs['ttfs_p99_latency'] = parameters['ttfs_p99_latency']
+
+        if 'language' in parameters and parameters['language']:
+            lang_code = parameters['language']
+            lang_enum = STTServiceFactory.SARVAM_LANGUAGE_MAP.get(lang_code)
+            if lang_enum:
+                kwargs['language'] = lang_enum
+            else:
+                logger.warning(
+                    f"Unknown Azure language '{lang_code}', using service default"
+                )
+
+        logger.info(f'Azure STT config: region={region}')
+
+        return AzureSTTService(**kwargs)
+
     @staticmethod
     def _create_assemblyai_stt(api_key: str, parameters: Dict[str, Any]):
         """Create AssemblyAI STT service"""
diff --git a/wavefront/server/apps/call_processing/call_processing/services/tts_service.py b/wavefront/server/apps/call_processing/call_processing/services/tts_service.py
index 0b6e6d1c..b0360373 100644
--- a/wavefront/server/apps/call_processing/call_processing/services/tts_service.py
+++ b/wavefront/server/apps/call_processing/call_processing/services/tts_service.py
@@ -16,14 +16,26 @@
 # Language for params
 from pipecat.transcriptions.language import Language
 
-# Add more as needed:
-# from pipecat.services.azure.tts import AzureTTSService
-# from pipecat.services.google.tts import GoogleTTSService
+from pipecat.services.azure.tts import AzureTTSService
 
 
 class TTSServiceFactory:
     """Factory for creating TTS service instances from configuration"""
 
+    AZURE_LANGUAGE_MAP = {
+        'en': Language.EN_US,
+        'hi': Language.HI_IN,
+        'ta': Language.TA_IN,
+        'te': Language.TE_IN,
+        'kn': Language.KN_IN,
+        'ml': Language.ML_IN,
+        'gu': Language.GU_IN,
+        'bn': Language.BN_IN,
+        'mr': Language.MR_IN,
+        'pa': Language.PA_IN,
+        'or': Language.OR_IN,
+    }
+
     @staticmethod
     def create_tts_service(tts_config: Dict[str, Any]):
         """
@@ -47,6 +59,7 @@ def create_tts_service(tts_config: Dict[str, Any]):
         """
         provider = tts_config['provider']
         api_key = tts_config['api_key']
+        region = tts_config.get('region')
         voice_id = tts_config['voice_id']
         parameters = tts_config.get('parameters', {})
 
@@ -65,6 +78,10 @@ def create_tts_service(tts_config: Dict[str, Any]):
             return TTSServiceFactory._create_cartesia_tts(api_key, voice_id, parameters)
         elif provider == 'sarvam':
             return TTSServiceFactory._create_sarvam_tts(api_key, voice_id, parameters)
+        elif provider == 'azure':
+            return TTSServiceFactory._create_azure_tts(
+                api_key, voice_id, region, parameters
+            )
         else:
             raise ValueError(f'Unsupported TTS provider: {provider}')
 
@@ -217,3 +234,51 @@ def _create_sarvam_tts(api_key: str, voice_id: str, parameters: Dict[str, Any]):
         return SarvamTTSService(
             api_key=api_key, voice_id=voice_id, model=model, params=input_params
         )
+
+    @staticmethod
+    def _create_azure_tts(
+        api_key: str, voice_id: str, region: str, parameters: Dict[str, Any]
+    ):
+        """Create Azure TTS service"""
+        if not region:
+            raise ValueError("Azure TTS requires 'region' to be set in the TTS config")
+
+        params_dict = {}
+
+        if 'language' in parameters and parameters['language']:
+            lang_code = parameters['language']
+            lang_enum = TTSServiceFactory.AZURE_LANGUAGE_MAP.get(lang_code)
+            if lang_enum:
+                params_dict['language'] = lang_enum
+            else:
+                logger.warning(
+                    f"Unknown Azure language '{lang_code}', using service default"
+                )
+        if 'style' in parameters and parameters['style']:
+            params_dict['style'] = parameters['style']
+        if 'style_degree' in parameters and parameters['style_degree']:
+            params_dict['style_degree'] = parameters['style_degree']
+        if 'role' in parameters and parameters['role']:
+            params_dict['role'] = parameters['role']
+        if 'rate' in parameters and parameters['rate']:
+            params_dict['rate'] = parameters['rate']
+        if 'pitch' in parameters and parameters['pitch']:
+            params_dict['pitch'] = parameters['pitch']
+        if 'volume' in parameters and parameters['volume']:
+            params_dict['volume'] = parameters['volume']
+
+        kwargs = {
+            'api_key': api_key,
+            'region': region,
+            'voice': voice_id,
+        }
+
+        if params_dict:
+            kwargs['params'] = AzureTTSService.InputParams(**params_dict)
+
+        if 'sample_rate' in parameters and parameters['sample_rate']:
+            kwargs['sample_rate'] = parameters['sample_rate']
+
+        logger.info(f'Azure TTS config: voice={voice_id}, region={region}')
+
+        return AzureTTSService(**kwargs)
diff --git a/wavefront/server/modules/db_repo_module/db_repo_module/alembic/versions/2026_03_19_1716-c153b06cfe7f_add_region_to_tts_stt_configs.py b/wavefront/server/modules/db_repo_module/db_repo_module/alembic/versions/2026_03_19_1716-c153b06cfe7f_add_region_to_tts_stt_configs.py
new file mode 100644
index 00000000..d7fdd2e3
--- /dev/null
+++ b/wavefront/server/modules/db_repo_module/db_repo_module/alembic/versions/2026_03_19_1716-c153b06cfe7f_add_region_to_tts_stt_configs.py
@@ -0,0 +1,33 @@
+"""add_region_to_tts_stt_configs
+
+Revision ID: c153b06cfe7f
+Revises: b92161a34bfc
+Create Date: 2026-03-19 17:16:45.273180
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = 'c153b06cfe7f'
+down_revision: Union[str, None] = 'b92161a34bfc'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        'tts_configs', sa.Column('region', sa.String(length=64), nullable=True)
+    )
+    op.add_column(
+        'stt_configs', sa.Column('region', sa.String(length=64), nullable=True)
+    )
+
+
+def downgrade() -> None:
+    op.drop_column('stt_configs', 'region')
+    op.drop_column('tts_configs', 'region')
diff --git a/wavefront/server/modules/db_repo_module/db_repo_module/models/stt_config.py b/wavefront/server/modules/db_repo_module/db_repo_module/models/stt_config.py
index 823daf16..806e0f4f 100644
--- a/wavefront/server/modules/db_repo_module/db_repo_module/models/stt_config.py
+++ b/wavefront/server/modules/db_repo_module/db_repo_module/models/stt_config.py
@@ -20,6 +20,7 @@ class SttConfig(Base):
     )
     provider: Mapped[str] = mapped_column(String(length=64), nullable=False)
     api_key: Mapped[str] = mapped_column(String(length=512), nullable=False)
+    region: Mapped[Optional[str]] = mapped_column(String(length=64), nullable=True)
     is_deleted: Mapped[bool] = mapped_column(default=False, nullable=False)
     created_at: Mapped[datetime] = mapped_column(default=func.now())
     updated_at: Mapped[datetime] = mapped_column(
diff --git a/wavefront/server/modules/db_repo_module/db_repo_module/models/tts_config.py b/wavefront/server/modules/db_repo_module/db_repo_module/models/tts_config.py
index 0c855d2c..33eded94 100644
--- a/wavefront/server/modules/db_repo_module/db_repo_module/models/tts_config.py
+++ b/wavefront/server/modules/db_repo_module/db_repo_module/models/tts_config.py
@@ -20,6 +20,7 @@ class TtsConfig(Base):
     )
     provider: Mapped[str] = mapped_column(String(length=64), nullable=False)
     api_key: Mapped[str] = mapped_column(String(length=512), nullable=False)
+    region: Mapped[Optional[str]] = mapped_column(String(length=64), nullable=True)
     is_deleted: Mapped[bool] = mapped_column(default=False, nullable=False)
     created_at: Mapped[datetime] = mapped_column(default=func.now())
     updated_at: Mapped[datetime] = mapped_column(
diff --git a/wavefront/server/modules/voice_agents_module/voice_agents_module/controllers/stt_config_controller.py b/wavefront/server/modules/voice_agents_module/voice_agents_module/controllers/stt_config_controller.py
index d0c94078..e4af6d80 100644
--- a/wavefront/server/modules/voice_agents_module/voice_agents_module/controllers/stt_config_controller.py
+++ b/wavefront/server/modules/voice_agents_module/voice_agents_module/controllers/stt_config_controller.py
@@ -45,6 +45,7 @@ async def create_stt_config(
         description=payload.description,
         provider=payload.provider.value,
         api_key=payload.api_key,
+        region=payload.region,
     )
 
     return JSONResponse(
@@ -151,6 +152,8 @@ async def update_stt_config(
         update_data['description'] = payload.description
     if payload.api_key is not UNSET:
         update_data['api_key'] = payload.api_key
+    if payload.region is not UNSET:
+        update_data['region'] = payload.region
 
     if not update_data:
         return JSONResponse(
diff --git a/wavefront/server/modules/voice_agents_module/voice_agents_module/controllers/tts_config_controller.py b/wavefront/server/modules/voice_agents_module/voice_agents_module/controllers/tts_config_controller.py
index 63a49266..a7b50ac5 100644
--- a/wavefront/server/modules/voice_agents_module/voice_agents_module/controllers/tts_config_controller.py
+++ b/wavefront/server/modules/voice_agents_module/voice_agents_module/controllers/tts_config_controller.py
@@ -45,6 +45,7 @@ async def create_tts_config(
         description=payload.description,
         provider=payload.provider.value,
         api_key=payload.api_key,
+        region=payload.region,
     )
 
     return JSONResponse(
@@ -151,6 +152,8 @@ async def update_tts_config(
         update_data['description'] = payload.description
     if payload.api_key is not UNSET:
         update_data['api_key'] = payload.api_key
+    if payload.region is not UNSET:
+        update_data['region'] = payload.region
 
     if not update_data:
         return JSONResponse(
diff --git a/wavefront/server/modules/voice_agents_module/voice_agents_module/models/stt_schemas.py b/wavefront/server/modules/voice_agents_module/voice_agents_module/models/stt_schemas.py
index ae3fb05d..050b61e5 100644
--- a/wavefront/server/modules/voice_agents_module/voice_agents_module/models/stt_schemas.py
+++ b/wavefront/server/modules/voice_agents_module/voice_agents_module/models/stt_schemas.py
@@ -32,12 +32,16 @@ class CreateSttConfigPayload(BaseModel):
     )
     provider: SttProvider = Field(..., description='STT provider')
     api_key: str = Field(..., description='API key for the STT provider')
+    region: Optional[str] = Field(
+        None, description='Region for the STT provider (e.g. Azure region)'
+    )
 
 
 class UpdateSttConfigPayload(BaseModel):
     display_name: Union[str, Any] = Field(default=UNSET)
     description: Union[str, None, Any] = Field(default=UNSET)
     api_key: Union[str, Any] = Field(default=UNSET)
+    region: Union[str, None, Any] = Field(default=UNSET)
 
 
 class SttConfigResponse(BaseModel):
@@ -45,6 +49,7 @@ class SttConfigResponse(BaseModel):
     display_name: str
     description: Optional[str]
     provider: str
+    region: Optional[str]
     is_deleted: bool
     created_at: datetime
     updated_at: datetime
diff --git a/wavefront/server/modules/voice_agents_module/voice_agents_module/models/tts_schemas.py b/wavefront/server/modules/voice_agents_module/voice_agents_module/models/tts_schemas.py
index 58ee2952..b26a4358 100644
--- a/wavefront/server/modules/voice_agents_module/voice_agents_module/models/tts_schemas.py
+++ b/wavefront/server/modules/voice_agents_module/voice_agents_module/models/tts_schemas.py
@@ -32,12 +32,16 @@ class CreateTtsConfigPayload(BaseModel):
     )
     provider: TtsProvider = Field(..., description='TTS provider')
     api_key: str = Field(..., description='API key for the TTS provider')
+    region: Optional[str] = Field(
+        None, description='Region for the TTS provider (e.g. Azure region)'
+    )
 
 
 class UpdateTtsConfigPayload(BaseModel):
     display_name: Union[str, Any] = Field(default=UNSET)
     description: Union[str, None, Any] = Field(default=UNSET)
     api_key: Union[str, Any] = Field(default=UNSET)
+    region: Union[str, None, Any] = Field(default=UNSET)
 
 
 class TtsConfigResponse(BaseModel):
@@ -45,6 +49,7 @@ class TtsConfigResponse(BaseModel):
     display_name: str
     description: Optional[str]
     provider: str
+    region: Optional[str]
     is_deleted: bool
     created_at: datetime
     updated_at: datetime
diff --git a/wavefront/server/modules/voice_agents_module/voice_agents_module/services/stt_config_service.py b/wavefront/server/modules/voice_agents_module/voice_agents_module/services/stt_config_service.py
index b55c441a..ac45f6ac 100644
--- a/wavefront/server/modules/voice_agents_module/voice_agents_module/services/stt_config_service.py
+++ b/wavefront/server/modules/voice_agents_module/voice_agents_module/services/stt_config_service.py
@@ -40,6 +40,7 @@ async def create_config(
         description: Optional[str] = None,
         provider: str = None,
         api_key: str = None,
+        region: Optional[str] = None,
     ) -> dict:
         """
         Create a new STT configuration
@@ -49,6 +50,7 @@ async def create_config(
             description: Optional description
             provider: STT provider
             api_key: API key for the STT provider
+            region: Region for the provider (e.g. Azure region)
 
         Returns:
             Created STT config as dict
@@ -62,6 +64,7 @@ async def create_config(
             description=description,
             provider=provider,
             api_key=api_key,
+            region=region,
         )
 
         # Convert to dict
diff --git a/wavefront/server/modules/voice_agents_module/voice_agents_module/services/tts_config_service.py b/wavefront/server/modules/voice_agents_module/voice_agents_module/services/tts_config_service.py
index fa655cdb..52f049d9 100644
--- a/wavefront/server/modules/voice_agents_module/voice_agents_module/services/tts_config_service.py
+++ b/wavefront/server/modules/voice_agents_module/voice_agents_module/services/tts_config_service.py
@@ -40,6 +40,7 @@ async def create_config(
         description: Optional[str] = None,
         provider: str = None,
         api_key: str = None,
+        region: Optional[str] = None,
     ) -> dict:
         """
         Create a new TTS configuration
@@ -49,6 +50,7 @@ async def create_config(
             description: Optional description
             provider: TTS provider
             api_key: API key for the TTS provider
+            region: Region for the provider (e.g. Azure region)
 
         Returns:
             Created TTS config as dict
@@ -62,6 +64,7 @@ async def create_config(
             description=description,
             provider=provider,
             api_key=api_key,
+            region=region,
         )
 
         # Convert to dict

From d830db263ad23172ffc001488ae8484acd2d653a Mon Sep 17 00:00:00 2001
From: rootflo-hardik <hardik@rootflo.ai>
Date: Fri, 20 Mar 2026 12:06:50 +0530
Subject: [PATCH 2/2] resolved review comments

---
 .../stt-configs/EditSttConfigDialog.tsx       | 19 ++++++++++++-------
 .../tts-configs/EditTtsConfigDialog.tsx       | 19 ++++++++++++-------
 .../call_processing/services/stt_service.py   | 16 +++++++++++++++-
 3 files changed, 39 insertions(+), 15 deletions(-)

diff --git a/wavefront/client/src/pages/apps/[appId]/voice-agents/stt-configs/EditSttConfigDialog.tsx b/wavefront/client/src/pages/apps/[appId]/voice-agents/stt-configs/EditSttConfigDialog.tsx
index c4eabf5a..f3763e20 100644
--- a/wavefront/client/src/pages/apps/[appId]/voice-agents/stt-configs/EditSttConfigDialog.tsx
+++ b/wavefront/client/src/pages/apps/[appId]/voice-agents/stt-configs/EditSttConfigDialog.tsx
@@ -30,13 +30,18 @@ import React, { useEffect, useState } from 'react';
 import { useForm } from 'react-hook-form';
 import { z } from 'zod';
 
-const updateSttConfigSchema = z.object({
-  display_name: z.string().min(1, 'Display name is required').max(100, 'Display name must be 100 characters or less'),
-  description: z.string().max(500, 'Description must be 500 characters or less').optional(),
-  provider: z.enum(['deepgram', 'sarvam', 'elevenlabs', 'azure'] as [string, ...string[]]),
-  api_key: z.string().optional(),
-  region: z.string().optional(),
-});
+const updateSttConfigSchema = z
+  .object({
+    display_name: z.string().min(1, 'Display name is required').max(100, 'Display name must be 100 characters or less'),
+    description: z.string().max(500, 'Description must be 500 characters or less').optional(),
+    provider: z.enum(['deepgram', 'sarvam', 'elevenlabs', 'azure'] as [string, ...string[]]),
+    api_key: z.string().optional(),
+    region: z.string().optional(),
+  })
+  .refine((data) => data.provider !== 'azure' || (data.region && data.region.trim().length > 0), {
+    message: 'Region is required for Azure',
+    path: ['region'],
+  });
 
 type UpdateSttConfigInput = z.infer<typeof updateSttConfigSchema>;
 
diff --git a/wavefront/client/src/pages/apps/[appId]/voice-agents/tts-configs/EditTtsConfigDialog.tsx b/wavefront/client/src/pages/apps/[appId]/voice-agents/tts-configs/EditTtsConfigDialog.tsx
index ef668f29..3a3e2c28 100644
--- a/wavefront/client/src/pages/apps/[appId]/voice-agents/tts-configs/EditTtsConfigDialog.tsx
+++ b/wavefront/client/src/pages/apps/[appId]/voice-agents/tts-configs/EditTtsConfigDialog.tsx
@@ -30,13 +30,18 @@ import React, { useEffect, useState } from 'react';
 import { useForm } from 'react-hook-form';
 import { z } from 'zod';
 
-const updateTtsConfigSchema = z.object({
-  display_name: z.string().min(1, 'Display name is required').max(100, 'Display name must be 100 characters or less'),
-  description: z.string().max(500, 'Description must be 500 characters or less').optional(),
-  provider: z.enum(['elevenlabs', 'deepgram', 'cartesia', 'sarvam', 'azure'] as [string, ...string[]]),
-  api_key: z.string().optional(),
-  region: z.string().optional(),
-});
+const updateTtsConfigSchema = z
+  .object({
+    display_name: z.string().min(1, 'Display name is required').max(100, 'Display name must be 100 characters or less'),
+    description: z.string().max(500, 'Description must be 500 characters or less').optional(),
+    provider: z.enum(['elevenlabs', 'deepgram', 'cartesia', 'sarvam', 'azure'] as [string, ...string[]]),
+    api_key: z.string().optional(),
+    region: z.string().optional(),
+  })
+  .refine((data) => data.provider !== 'azure' || (data.region && data.region.trim().length > 0), {
+    message: 'Region is required for Azure',
+    path: ['region'],
+  });
 
 type UpdateTtsConfigInput = z.infer<typeof updateTtsConfigSchema>;
 
diff --git a/wavefront/server/apps/call_processing/call_processing/services/stt_service.py b/wavefront/server/apps/call_processing/call_processing/services/stt_service.py
index e69b08a6..65255e6a 100644
--- a/wavefront/server/apps/call_processing/call_processing/services/stt_service.py
+++ b/wavefront/server/apps/call_processing/call_processing/services/stt_service.py
@@ -181,6 +181,20 @@ def _create_sarvam_stt(api_key: str, parameters: Dict[str, Any]):
         'or': 'ori',
     }
 
+    AZURE_LANGUAGE_MAP = {
+        'en': Language.EN_US,
+        'hi': Language.HI_IN,
+        'ta': Language.TA_IN,
+        'te': Language.TE_IN,
+        'kn': Language.KN_IN,
+        'ml': Language.ML_IN,
+        'gu': Language.GU_IN,
+        'bn': Language.BN_IN,
+        'mr': Language.MR_IN,
+        'pa': Language.PA_IN,
+        'or': Language.OR_IN,
+    }
+
     @staticmethod
     def _create_elevenlabs_stt(api_key: str, parameters: Dict[str, Any]):
         """Create ElevenLabs Realtime STT service (WebSocket streaming, scribe_v2_realtime)"""
@@ -238,7 +252,7 @@ def _create_azure_stt(api_key: str, region: str, parameters: Dict[str, Any]):
 
         if 'language' in parameters and parameters['language']:
             lang_code = parameters['language']
-            lang_enum = STTServiceFactory.SARVAM_LANGUAGE_MAP.get(lang_code)
+            lang_enum = STTServiceFactory.AZURE_LANGUAGE_MAP.get(lang_code)
             if lang_enum:
                 kwargs['language'] = lang_enum
             else: