From bd1a8dcc3a3e27d16f8b01b7180d139e86070b76 Mon Sep 17 00:00:00 2001
From: Hk-Gosuto <yominogosuto@gmail.com>
Date: Tue, 26 Mar 2024 17:02:41 +0800
Subject: [PATCH] fix: #236

---
 app/components/chat.tsx       |  3 +++
 app/components/stt-config.tsx | 41 +++++++++++++++++++----------------
 app/constant.ts               |  1 +
 app/utils/speech.ts           |  2 ++
 4 files changed, 28 insertions(+), 19 deletions(-)

diff --git a/app/components/chat.tsx b/app/components/chat.tsx
index 4ad66a8ce..ae9f5881d 100644
--- a/app/components/chat.tsx
+++ b/app/components/chat.tsx
@@ -68,6 +68,7 @@ import {
   getMessageImages,
   isVisionModel,
   compressImage,
+  isFirefox,
 } from "../utils";
 
 import dynamic from "next/dynamic";
@@ -92,6 +93,7 @@ import { useNavigate } from "react-router-dom";
 import {
   CHAT_PAGE_SIZE,
   DEFAULT_STT_ENGINE,
+  FIREFOX_DEFAULT_STT_ENGINE,
   LAST_INPUT_KEY,
   ModelProvider,
   Path,
@@ -903,6 +905,7 @@ function _Chat() {
       }
     });
     // eslint-disable-next-line react-hooks/exhaustive-deps
+    if (isFirefox()) config.sttConfig.engine = FIREFOX_DEFAULT_STT_ENGINE;
     setSpeechApi(
       config.sttConfig.engine === DEFAULT_STT_ENGINE
         ? new WebTranscriptionApi((transcription) =>
diff --git a/app/components/stt-config.tsx b/app/components/stt-config.tsx
index 8ba9176d9..f83d28030 100644
--- a/app/components/stt-config.tsx
+++ b/app/components/stt-config.tsx
@@ -3,6 +3,7 @@ import { STTConfig, STTConfigValidator } from "../store";
 import Locale from "../locales";
 import { ListItem, Select } from "./ui-lib";
 import { DEFAULT_STT_ENGINES } from "../constant";
+import { isFirefox } from "../utils";
 
 export function STTConfigList(props: {
   sttConfig: STTConfig;
@@ -24,25 +25,27 @@ export function STTConfigList(props: {
           }
         ></input>
       </ListItem>
-      <ListItem title={Locale.Settings.STT.Engine.Title}>
-        <Select
-          value={props.sttConfig.engine}
-          onChange={(e) => {
-            props.updateConfig(
-              (config) =>
-                (config.engine = STTConfigValidator.engine(
-                  e.currentTarget.value,
-                )),
-            );
-          }}
-        >
-          {DEFAULT_STT_ENGINES.map((v, i) => (
-            <option value={v} key={i}>
-              {v}
-            </option>
-          ))}
-        </Select>
-      </ListItem>
+      {!isFirefox() && (
+        <ListItem title={Locale.Settings.STT.Engine.Title}>
+          <Select
+            value={props.sttConfig.engine}
+            onChange={(e) => {
+              props.updateConfig(
+                (config) =>
+                  (config.engine = STTConfigValidator.engine(
+                    e.currentTarget.value,
+                  )),
+              );
+            }}
+          >
+            {DEFAULT_STT_ENGINES.map((v, i) => (
+              <option value={v} key={i}>
+                {v}
+              </option>
+            ))}
+          </Select>
+        </ListItem>
+      )}
     </>
   );
 }
diff --git a/app/constant.ts b/app/constant.ts
index 4712a1019..e081e2bff 100644
--- a/app/constant.ts
+++ b/app/constant.ts
@@ -136,6 +136,7 @@ export const DEFAULT_TTS_VOICES = [
 
 export const DEFAULT_STT_ENGINE = "WebAPI";
 export const DEFAULT_STT_ENGINES = ["WebAPI", "OpenAI Whisper"];
+export const FIREFOX_DEFAULT_STT_ENGINE = "OpenAI Whisper";
 
 export const DEFAULT_MODELS = [
   {
diff --git a/app/utils/speech.ts b/app/utils/speech.ts
index 06883d703..dc8102879 100644
--- a/app/utils/speech.ts
+++ b/app/utils/speech.ts
@@ -1,5 +1,6 @@
 import { ChatGPTApi } from "../client/platforms/openai";
 import { getSTTLang } from "../locales";
+import { isFirefox } from "../utils";
 
 export type TranscriptionCallback = (transcription: string) => void;
 
@@ -94,6 +95,7 @@ export class WebTranscriptionApi extends SpeechApi {
 
   constructor(transcriptionCallback?: TranscriptionCallback) {
     super();
+    if (isFirefox()) return;
     const SpeechRecognition =
       (window as any).SpeechRecognition ||
       (window as any).webkitSpeechRecognition;