diff --git a/app/client/platforms/alibaba.ts b/app/client/platforms/alibaba.ts
index 86229a147..57f8bc3fd 100644
--- a/app/client/platforms/alibaba.ts
+++ b/app/client/platforms/alibaba.ts
@@ -13,6 +13,7 @@ import {
   LLMApi,
   LLMModel,
   SpeechOptions,
+  TranscriptionOptions,
   MultimodalContent,
 } from "../api";
 import Locale from "../../locales";
@@ -89,6 +90,10 @@ export class QwenApi implements LLMApi {
     throw new Error("Method not implemented.");
   }
 
+  transcription(options: TranscriptionOptions): Promise<string> {
+    throw new Error("Method not implemented.");
+  }
+
   async chat(options: ChatOptions) {
     const messages = options.messages.map((v) => ({
       role: v.role,
diff --git a/app/client/platforms/anthropic.ts b/app/client/platforms/anthropic.ts
index 1a83bd53a..24f76f31d 100644
--- a/app/client/platforms/anthropic.ts
+++ b/app/client/platforms/anthropic.ts
@@ -1,5 +1,11 @@
 import { Anthropic, ApiPath } from "@/app/constant";
-import { ChatOptions, getHeaders, LLMApi, SpeechOptions } from "../api";
+import {
+  ChatOptions,
+  getHeaders,
+  LLMApi,
+  SpeechOptions,
+  TranscriptionOptions,
+} from "../api";
 import {
   useAccessStore,
   useAppConfig,
@@ -77,6 +83,10 @@ export class ClaudeApi implements LLMApi {
     throw new Error("Method not implemented.");
   }
 
+  transcription(options: TranscriptionOptions): Promise<string> {
+    throw new Error("Method not implemented.");
+  }
+
   extractMessage(res: any) {
     console.log("[Response] claude response: ", res);
 
diff --git a/app/client/platforms/baidu.ts b/app/client/platforms/baidu.ts
index 2511a696b..a809183c0 100644
--- a/app/client/platforms/baidu.ts
+++ b/app/client/platforms/baidu.ts
@@ -15,6 +15,7 @@ import {
   LLMModel,
   MultimodalContent,
   SpeechOptions,
+  TranscriptionOptions,
 } from "../api";
 import Locale from "../../locales";
 import {
@@ -81,6 +82,10 @@ export class ErnieApi implements LLMApi {
     throw new Error("Method not implemented.");
   }
 
+  transcription(options: TranscriptionOptions): Promise<string> {
+    throw new Error("Method not implemented.");
+  }
+
   async chat(options: ChatOptions) {
     const messages = options.messages.map((v) => ({
       // "error_code": 336006, "error_msg": "the role of message with even index in the messages must be user or function",
diff --git a/app/client/platforms/bytedance.ts b/app/client/platforms/bytedance.ts
index 000a9e278..25b45e485 100644
--- a/app/client/platforms/bytedance.ts
+++ b/app/client/platforms/bytedance.ts
@@ -14,6 +14,7 @@ import {
   LLMModel,
   MultimodalContent,
   SpeechOptions,
+  TranscriptionOptions,
 } from "../api";
 import Locale from "../../locales";
 import {
@@ -83,6 +84,10 @@ export class DoubaoApi implements LLMApi {
     throw new Error("Method not implemented.");
   }
 
+  transcription(options: TranscriptionOptions): Promise<string> {
+    throw new Error("Method not implemented.");
+  }
+
   async chat(options: ChatOptions) {
     const messages = options.messages.map((v) => ({
       role: v.role,
diff --git a/app/client/platforms/google.ts b/app/client/platforms/google.ts
index 7265a500b..40d49373e 100644
--- a/app/client/platforms/google.ts
+++ b/app/client/platforms/google.ts
@@ -6,6 +6,7 @@ import {
   LLMModel,
   LLMUsage,
   SpeechOptions,
+  TranscriptionOptions,
 } from "../api";
 import {
   useAccessStore,
@@ -68,6 +69,10 @@ export class GeminiProApi implements LLMApi {
     throw new Error("Method not implemented.");
   }
 
+  transcription(options: TranscriptionOptions): Promise<string> {
+    throw new Error("Method not implemented.");
+  }
+
   async chat(options: ChatOptions): Promise<void> {
     const apiClient = this;
     let multimodal = false;
diff --git a/app/client/platforms/iflytek.ts b/app/client/platforms/iflytek.ts
index 55a39d0cc..fcff72ca6 100644
--- a/app/client/platforms/iflytek.ts
+++ b/app/client/platforms/iflytek.ts
@@ -13,6 +13,7 @@ import {
   LLMApi,
   LLMModel,
   SpeechOptions,
+  TranscriptionOptions,
 } from "../api";
 import Locale from "../../locales";
 import {
@@ -64,6 +65,10 @@ export class SparkApi implements LLMApi {
     throw new Error("Method not implemented.");
   }
 
+  transcription(options: TranscriptionOptions): Promise<string> {
+    throw new Error("Method not implemented.");
+  }
+
   async chat(options: ChatOptions) {
     const messages: ChatOptions["messages"] = [];
     for (const v of options.messages) {
diff --git a/app/client/platforms/moonshot.ts b/app/client/platforms/moonshot.ts
index e0ef3494f..b32e4213a 100644
--- a/app/client/platforms/moonshot.ts
+++ b/app/client/platforms/moonshot.ts
@@ -20,6 +20,7 @@ import {
   LLMApi,
   LLMModel,
   SpeechOptions,
+  TranscriptionOptions,
 } from "../api";
 import { getClientConfig } from "@/app/config/client";
 import { getMessageTextContent } from "@/app/utils";
@@ -63,6 +64,10 @@ export class MoonshotApi implements LLMApi {
     throw new Error("Method not implemented.");
   }
 
+  transcription(options: TranscriptionOptions): Promise<string> {
+    throw new Error("Method not implemented.");
+  }
+
   async chat(options: ChatOptions) {
     const messages: ChatOptions["messages"] = [];
     for (const v of options.messages) {
diff --git a/app/client/platforms/openai.ts b/app/client/platforms/openai.ts
index 0ba062b75..029eeb074 100644
--- a/app/client/platforms/openai.ts
+++ b/app/client/platforms/openai.ts
@@ -34,6 +34,7 @@ import {
   LLMUsage,
   MultimodalContent,
   SpeechOptions,
+  TranscriptionOptions,
 } from "../api";
 import Locale from "../../locales";
 import { getClientConfig } from "@/app/config/client";
diff --git a/app/client/platforms/tencent.ts b/app/client/platforms/tencent.ts
index 3610fac0a..67ad64dcb 100644
--- a/app/client/platforms/tencent.ts
+++ b/app/client/platforms/tencent.ts
@@ -9,6 +9,7 @@ import {
   LLMModel,
   MultimodalContent,
   SpeechOptions,
+  TranscriptionOptions,
 } from "../api";
 import Locale from "../../locales";
 import {
@@ -93,6 +94,10 @@ export class HunyuanApi implements LLMApi {
     throw new Error("Method not implemented.");
   }
 
+  transcription(options: TranscriptionOptions): Promise<string> {
+    throw new Error("Method not implemented.");
+  }
+
   async chat(options: ChatOptions) {
     const visionModel = isVisionModel(options.config.model);
     const messages = options.messages.map((v, index) => ({
diff --git a/app/components/chat.tsx b/app/components/chat.tsx
index 43718aa32..a1584d899 100644
--- a/app/components/chat.tsx
+++ b/app/components/chat.tsx
@@ -99,6 +99,7 @@ import {
 } from "./ui-lib";
 import { useNavigate } from "react-router-dom";
 import {
+  CHAT_PAGE_SIZE,
   DEFAULT_STT_ENGINE,
   DEFAULT_TTS_ENGINE,
   FIREFOX_DEFAULT_STT_ENGINE,
diff --git a/app/locales/cn.ts b/app/locales/cn.ts
index e5bcca0ed..eaa799a04 100644
--- a/app/locales/cn.ts
+++ b/app/locales/cn.ts
@@ -538,6 +538,16 @@ const cn = {
         SubTitle: "生成语音的速度",
       },
     },
+    STT: {
+      Enable: {
+        Title: "启用语音转文本",
+        SubTitle: "启用语音转文本",
+      },
+      Engine: {
+        Title: "转换引擎",
+        SubTitle: "音频转换引擎",
+      },
+    },
   },
   Store: {
     DefaultTopic: "新的聊天",
diff --git a/app/locales/en.ts b/app/locales/en.ts
index 120457522..f715d0889 100644
--- a/app/locales/en.ts
+++ b/app/locales/en.ts
@@ -546,6 +546,16 @@ const en: LocaleType = {
       },
       Engine: "TTS Engine",
     },
+    STT: {
+      Enable: {
+        Title: "Enable STT",
+        SubTitle: "Enable Speech-to-Text",
+      },
+      Engine: {
+        Title: "STT Engine",
+        SubTitle: "Text-to-Speech Engine",
+      },
+    },
   },
   Store: {
     DefaultTopic: "New Conversation",