feat: voice mode prompt template

backend/open_webui/config.py

@@ -1817,6 +1817,38 @@ Output:
 #### Output:
 """
 
+
+VOICE_MODE_PROMPT_TEMPLATE = PersistentConfig(
+    "VOICE_MODE_PROMPT_TEMPLATE",
+    "task.voice.prompt_template",
+    os.environ.get("VOICE_MODE_PROMPT_TEMPLATE", ""),
+)
+
+DEFAULT_VOICE_MODE_PROMPT_TEMPLATE = """You are a friendly, concise voice assistant.
+
+Everything you say will be spoken aloud.
+Keep responses short, clear, and natural.
+
+STYLE:
+- Use simple words and short sentences.
+- Sound warm and conversational.
+- Avoid long explanations, lists, or complex phrasing.
+
+BEHAVIOR:
+- Give the quickest helpful answer first.
+- Offer extra detail only if needed.
+- Ask for clarification only when necessary.
+
+VOICE OPTIMIZATION:
+- Break information into small, easy-to-hear chunks.
+- Avoid dense wording or anything that sounds like reading text.
+
+ERROR HANDLING:
+- If unsure, say so briefly and offer options.
+- If something is unsafe or impossible, decline kindly and suggest a safe alternative.
+
+Stay consistent, helpful, and easy to listen to."""
+
 TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE = PersistentConfig(
     "TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE",
     "task.tools.prompt_template",

backend/open_webui/main.py

@@ -429,6 +429,7 @@ from open_webui.config import (
     TAGS_GENERATION_PROMPT_TEMPLATE,
     IMAGE_PROMPT_GENERATION_PROMPT_TEMPLATE,
     TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE,
+    VOICE_MODE_PROMPT_TEMPLATE,
     QUERY_GENERATION_PROMPT_TEMPLATE,
     AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE,
     AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH,
@@ -1208,6 +1209,7 @@ app.state.config.AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE = (
 app.state.config.AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH = (
     AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH
 )
+app.state.config.VOICE_MODE_PROMPT_TEMPLATE = VOICE_MODE_PROMPT_TEMPLATE
 
 
 ########################################

backend/open_webui/routers/tasks.py

@@ -33,6 +33,7 @@ from open_webui.config import (
     DEFAULT_AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE,
     DEFAULT_EMOJI_GENERATION_PROMPT_TEMPLATE,
     DEFAULT_MOA_GENERATION_PROMPT_TEMPLATE,
+    DEFAULT_VOICE_MODE_PROMPT_TEMPLATE,
 )
 from open_webui.env import SRC_LOG_LEVELS
 
@@ -68,6 +69,7 @@ async def get_task_config(request: Request, user=Depends(get_verified_user)):
         "ENABLE_RETRIEVAL_QUERY_GENERATION": request.app.state.config.ENABLE_RETRIEVAL_QUERY_GENERATION,
         "QUERY_GENERATION_PROMPT_TEMPLATE": request.app.state.config.QUERY_GENERATION_PROMPT_TEMPLATE,
         "TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE": request.app.state.config.TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE,
+        "VOICE_MODE_PROMPT_TEMPLATE": request.app.state.config.VOICE_MODE_PROMPT_TEMPLATE,
     }
 
 
@@ -87,6 +89,7 @@ class TaskConfigForm(BaseModel):
     ENABLE_RETRIEVAL_QUERY_GENERATION: bool
     QUERY_GENERATION_PROMPT_TEMPLATE: str
     TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE: str
+    VOICE_MODE_PROMPT_TEMPLATE: Optional[str]
 
 
 @router.post("/config/update")
@@ -136,6 +139,10 @@ async def update_task_config(
         form_data.TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE
     )
 
+    request.app.state.config.VOICE_MODE_PROMPT_TEMPLATE = (
+        form_data.VOICE_MODE_PROMPT_TEMPLATE
+    )
+
     return {
         "TASK_MODEL": request.app.state.config.TASK_MODEL,
         "TASK_MODEL_EXTERNAL": request.app.state.config.TASK_MODEL_EXTERNAL,
@@ -152,6 +159,7 @@ async def update_task_config(
         "ENABLE_RETRIEVAL_QUERY_GENERATION": request.app.state.config.ENABLE_RETRIEVAL_QUERY_GENERATION,
         "QUERY_GENERATION_PROMPT_TEMPLATE": request.app.state.config.QUERY_GENERATION_PROMPT_TEMPLATE,
         "TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE": request.app.state.config.TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE,
+        "VOICE_MODE_PROMPT_TEMPLATE": request.app.state.config.VOICE_MODE_PROMPT_TEMPLATE,
     }
 
 

backend/open_webui/utils/middleware.py

@@ -104,6 +104,7 @@ from open_webui.utils.mcp.client import MCPClient
 
 from open_webui.config import (
     CACHE_DIR,
+    DEFAULT_VOICE_MODE_PROMPT_TEMPLATE,
     DEFAULT_TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE,
     DEFAULT_CODE_INTERPRETER_PROMPT,
     CODE_INTERPRETER_BLOCKED_MODULES,
@@ -1237,6 +1238,18 @@ async def process_chat_payload(request, form_data, user, metadata, model):
 
     features = form_data.pop("features", None)
     if features:
+        if "voice" in features and features["voice"]:
+            if request.app.state.config.VOICE_MODE_PROMPT_TEMPLATE != None:
+                if request.app.state.config.VOICE_MODE_PROMPT_TEMPLATE != "":
+                    template = request.app.state.config.VOICE_MODE_PROMPT_TEMPLATE
+                else:
+                    template = DEFAULT_VOICE_MODE_PROMPT_TEMPLATE
+
+                form_data["messages"] = add_or_update_system_message(
+                    template,
+                    form_data["messages"],
+                )
+
         if "memory" in features and features["memory"]:
             form_data = await chat_memory_handler(
                 request, form_data, extra_params, user

src/lib/components/admin/Settings/Interface.svelte

@@ -41,7 +41,8 @@
 		ENABLE_SEARCH_QUERY_GENERATION: true,
 		ENABLE_RETRIEVAL_QUERY_GENERATION: true,
 		QUERY_GENERATION_PROMPT_TEMPLATE: '',
-		TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE: ''
+		TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE: '',
+		VOICE_MODE_PROMPT_TEMPLATE: ''
 	};
 
 	let promptSuggestions = [];
@@ -237,6 +238,41 @@
 					</div>
 				{/if}
 
+				<div class="mb-2.5 flex w-full items-center justify-between">
+					<div class=" self-center text-xs font-medium">
+						{$i18n.t('Voice Mode Custom Prompt')}
+					</div>
+
+					<Switch
+						state={taskConfig.VOICE_MODE_PROMPT_TEMPLATE != null}
+						on:change={(e) => {
+							if (e.detail) {
+								taskConfig.VOICE_MODE_PROMPT_TEMPLATE = '';
+							} else {
+								taskConfig.VOICE_MODE_PROMPT_TEMPLATE = null;
+							}
+						}}
+					/>
+				</div>
+
+				{#if taskConfig.VOICE_MODE_PROMPT_TEMPLATE != null}
+					<div class="mb-2.5">
+						<div class=" mb-1 text-xs font-medium">{$i18n.t('Voice Mode Prompt')}</div>
+
+						<Tooltip
+							content={$i18n.t('Leave empty to use the default prompt, or enter a custom prompt')}
+							placement="top-start"
+						>
+							<Textarea
+								bind:value={taskConfig.VOICE_MODE_PROMPT_TEMPLATE}
+								placeholder={$i18n.t(
+									'Leave empty to use the default prompt, or enter a custom prompt'
+								)}
+							/>
+						</Tooltip>
+					</div>
+				{/if}
+
 				<div class="mb-2.5 flex w-full items-center justify-between">
 					<div class=" self-center text-xs font-medium">
 						{$i18n.t('Follow Up Generation')}

src/lib/components/chat/Chat.svelte

@@ -1792,6 +1792,7 @@
 
 		if ($config?.features)
 			features = {
+				voice: $showCallOverlay,
 				image_generation:
 					$config?.features?.enable_image_generation &&
 					($user?.role === 'admin' || $user?.permissions?.features?.image_generation)