diff --git a/astrbot/core/config/default.py b/astrbot/core/config/default.py
index 26eab94f9..53e2db11e 100644
--- a/astrbot/core/config/default.py
+++ b/astrbot/core/config/default.py
@@ -1976,26 +1976,28 @@
                         "hint": "留空代表不使用。可用于不支持视觉模态的聊天模型。",
                     },
                     "provider_stt_settings.enable": {
-                        "description": "默认启用语音转文本",
+                        "description": "启用语音转文本",
                         "type": "bool",
+                        "hint": "STT 总开关。",
                     },
                     "provider_stt_settings.provider_id": {
-                        "description": "语音转文本模型",
+                        "description": "默认语音转文本模型",
                         "type": "string",
-                        "hint": "留空代表不使用。",
+                        "hint": "用户也可使用 /provider 指令单独选择会话的 STT 模型。",
                         "_special": "select_provider_stt",
                         "condition": {
                             "provider_stt_settings.enable": True,
                         },
                     },
                     "provider_tts_settings.enable": {
-                        "description": "默认启用文本转语音",
+                        "description": "启用文本转语音",
                         "type": "bool",
+                        "hint": "TTS 总开关。当关闭时，会话启用 TTS 也不会生效。",
                     },
                     "provider_tts_settings.provider_id": {
-                        "description": "文本转语音模型",
+                        "description": "默认文本转语音模型",
                         "type": "string",
-                        "hint": "留空代表不使用。",
+                        "hint": "用户也可使用 /provider 单独选择会话的 TTS 模型。",
                         "_special": "select_provider_tts",
                         "condition": {
                             "provider_tts_settings.enable": True,
@@ -2112,7 +2114,7 @@
                         "description": "额外前缀提示词",
                         "type": "string",
                     },
-                    "provider_settings.dual_output": {
+                    "provider_tts_settings.dual_output": {
                         "description": "开启 TTS 时同时输出语音和文字内容",
                         "type": "bool",
                     },
diff --git a/astrbot/core/pipeline/preprocess_stage/stage.py b/astrbot/core/pipeline/preprocess_stage/stage.py
index 3e0d4e50f..50dc85a4b 100644
--- a/astrbot/core/pipeline/preprocess_stage/stage.py
+++ b/astrbot/core/pipeline/preprocess_stage/stage.py
@@ -46,6 +46,9 @@ async def process(
             ctx = self.plugin_manager.context
             stt_provider = ctx.get_using_stt_provider(event.unified_msg_origin)
             if not stt_provider:
+                logger.warning(
+                    f"会话 {event.unified_msg_origin} 未配置语音转文本模型。"
+                )
                 return
             message_chain = event.get_messages()
             for idx, component in enumerate(message_chain):
diff --git a/astrbot/core/pipeline/result_decorate/stage.py b/astrbot/core/pipeline/result_decorate/stage.py
index 4964dd68c..094d21768 100644
--- a/astrbot/core/pipeline/result_decorate/stage.py
+++ b/astrbot/core/pipeline/result_decorate/stage.py
@@ -183,9 +183,13 @@ async def process(
             if (
                 self.ctx.astrbot_config["provider_tts_settings"]["enable"]
                 and result.is_llm_result()
-                and tts_provider
                 and SessionServiceManager.should_process_tts_request(event)
             ):
+                if not tts_provider:
+                    logger.warning(
+                        f"会话 {event.unified_msg_origin} 未配置文本转语音模型。"
+                    )
+                    return
                 new_chain = []
                 for comp in result.chain:
                     if isinstance(comp, Plain) and len(comp.text) > 1:
diff --git a/packages/astrbot/main.py b/packages/astrbot/main.py
index 5d33512b4..327dd8f58 100644
--- a/packages/astrbot/main.py
+++ b/packages/astrbot/main.py
@@ -310,17 +310,27 @@ async def t2i(self, event: AstrMessageEvent):
     @filter.command("tts")
     async def tts(self, event: AstrMessageEvent):
         """开关文本转语音（会话级别）"""
-        session_id = event.unified_msg_origin
-        current_status = SessionServiceManager.is_tts_enabled_for_session(session_id)
+        umo = event.unified_msg_origin
+        ses_tts = SessionServiceManager.is_tts_enabled_for_session(umo)
+        cfg = self.context.get_config(umo=umo)
+        tts_enable = cfg["provider_tts_settings"]["enable"]
 
         # 切换状态
-        new_status = not current_status
-        SessionServiceManager.set_tts_status_for_session(session_id, new_status)
+        new_status = not ses_tts
+        SessionServiceManager.set_tts_status_for_session(umo, new_status)
 
         status_text = "已开启" if new_status else "已关闭"
-        event.set_result(
-            MessageEventResult().message(f"{status_text}当前会话的文本转语音。")
-        )
+
+        if new_status and not tts_enable:
+            event.set_result(
+                MessageEventResult().message(
+                    f"{status_text}当前会话的文本转语音。但 TTS 功能在配置中未启用，请前往 WebUI 开启。"
+                )
+            )
+        else:
+            event.set_result(
+                MessageEventResult().message(f"{status_text}当前会话的文本转语音。")
+            )
 
     @filter.command("sid")
     async def sid(self, event: AstrMessageEvent):