1, add voice volume

2, code optimization

app/models/schema.py

@@ -98,6 +98,7 @@ class VideoParams:
     video_language: Optional[str] = ""  # auto detect
 
     voice_name: Optional[str] = ""
+    voice_volume: Optional[float] = 1.0
     bgm_type: Optional[str] = "random"
     bgm_file: Optional[str] = ""
     bgm_volume: Optional[float] = 0.2
@@ -231,18 +232,18 @@ class VideoTermsResponse(BaseResponse):
         }
 
 
-class BgmListResponse(BaseResponse):
+class BgmRetrieveResponse(BaseResponse):
     class Config:
         json_schema_extra = {
             "example": {
                 "status": 200,
                 "message": "success",
                 "data": {
-                    "bgm_list": [
+                    "files": [
                         {
-                            "filename": "output000.mp3",
+                            "name": "output013.mp3",
-                            "size": 2249517,
+                            "size": 1891269,
-                            "filepath": "C:\\Users\\cathy\\Desktop\\MoneyPrinterTurbo\\resource\\songs\\output000.mp3"
+                            "file": "/MoneyPrinterTurbo/resource/songs/output013.mp3"
                         }
                     ]
                 }
@@ -257,7 +258,7 @@ class BgmUploadResponse(BaseResponse):
                 "status": 200,
                 "message": "success",
                 "data": {
-                    "uploaded_path": "/root/home/MoneyPrinterTurbo/resource/songs/example.mp3"
+                    "file": "/MoneyPrinterTurbo/resource/songs/example.mp3"
                 }
             },
         }

app/services/video.py

@@ -229,6 +229,11 @@ def generate_video(video_path: str,
     result = CompositeVideoClip(clips)
 
     audio = AudioFileClip(audio_path)
+    try:
+        audio = audio.volumex(params.voice_volume)
+    except Exception as e:
+        logger.warning(f"failed to set audio volume: {e}")
+
     result = result.set_audio(audio)
 
     temp_output_file = f"{output_file}.temp.mp4"
@@ -302,6 +307,8 @@ if __name__ == "__main__":
     cfg.n_threads = 2
     cfg.paragraph_number = 1
 
+    cfg.voice_volume = 3.0
+
     generate_video(video_path=video_file,
                    audio_path=audio_file,
                    subtitle_path=subtitle_file,

webui/Main.py

@@ -224,7 +224,7 @@ with left_panel:
         params.video_script = st.text_area(
             tr("Video Script"),
             value=st.session_state['video_script'],
-            height=180
+            height=280
         )
         if st.button(tr("Generate Video Keywords"), key="auto_generate_terms"):
             if not params.video_script:
@@ -295,6 +295,8 @@ with middle_panel:
         cfg['voice_name'] = voice_name
         save_config()
 
+        params.voice_volume = st.selectbox(tr("Speech Volume"),
+                                           options=[0.6, 0.8, 1.0, 1.2, 1.5, 2.0, 3.0, 4.0, 5.0], index=2)
         bgm_options = [
             (tr("No Background Music"), ""),
             (tr("Random Background Music"), "random"),
@@ -373,6 +375,19 @@ if start_button:
     logger.info(utils.to_json(params))
     scroll_to_bottom()
 
-    tm.start(task_id=task_id, params=params)
+    result = tm.start(task_id=task_id, params=params)
+
+    video_files = result.get("videos", [])
+    st.success(tr("Video Generation Completed"))
+    try:
+        if video_files:
+            # center the video player
+            player_cols = st.columns(len(video_files) * 2 + 1)
+            for i, url in enumerate(video_files):
+                player_cols[i * 2 + 1].video(url)
+    except Exception as e:
+        pass
+
     open_task_folder(task_id)
     logger.info(tr("Video Generation Completed"))
+    scroll_to_bottom()

webui/i18n/de.json

@@ -23,6 +23,7 @@
     "Number of Videos Generated Simultaneously": "Anzahl der parallel generierten Videos",
     "Audio Settings": "**Audio Einstellungen**",
     "Speech Synthesis": "Sprachausgabe",
+    "Speech Volume": "Lautstärke der Sprachausgabe",
     "Male": "Männlich",
     "Female": "Weiblich",
     "Background Music": "Hintergrundmusik",
@@ -46,6 +47,7 @@
     "Video Script and Subject Cannot Both Be Empty": "Das Video-Thema und Drehbuch dürfen nicht beide leer sein",
     "Generating Video": "Video wird erstellt, bitte warten...",
     "Start Generating Video": "Beginne mit der Generierung",
-    "Video Generation Completed": "Video erfolgreich generiert"
+    "Video Generation Completed": "Video erfolgreich generiert",
+    "You can download the generated video from the following links": "Sie können das generierte Video über die folgenden Links herunterladen"
   }
 }

webui/i18n/en.json

@@ -23,6 +23,7 @@
     "Number of Videos Generated Simultaneously": "Number of Videos Generated Simultaneously",
     "Audio Settings": "**Audio Settings**",
     "Speech Synthesis": "Speech Synthesis Voice",
+    "Speech Volume": "Speech Volume (1.0 represents 100%)",
     "Male": "Male",
     "Female": "Female",
     "Background Music": "Background Music",
@@ -46,6 +47,7 @@
     "Video Script and Subject Cannot Both Be Empty": "Video Subject and Video Script cannot both be empty",
     "Generating Video": "Generating video, please wait...",
     "Start Generating Video": "Start Generating Video",
-    "Video Generation Completed": "Video Generation Completed"
+    "Video Generation Completed": "Video Generation Completed",
+    "You can download the generated video from the following links": "You can download the generated video from the following links"
   }
 }

webui/i18n/zh.json

@@ -22,7 +22,8 @@
     "Clip Duration": "视频片段最大时长(秒)",
     "Number of Videos Generated Simultaneously": "同时生成视频数量",
     "Audio Settings": "**音频设置**",
-    "Speech Synthesis": "朗读声音",
+    "Speech Synthesis": "朗读声音（:red[尽量与文案语言保持一致]）",
+    "Speech Volume": "朗读音量（1.0表示100%）",
     "Male": "男性",
     "Female": "女性",
     "Background Music": "背景音乐",
@@ -46,6 +47,7 @@
     "Video Script and Subject Cannot Both Be Empty": "视频主题 和 视频文案，不能同时为空",
     "Generating Video": "正在生成视频，请稍候...",
     "Start Generating Video": "开始生成视频",
-    "Video Generation Completed": "视频生成完成"
+    "Video Generation Completed": "视频生成完成",
+    "You can download the generated video from the following links": "你可以从以下链接下载生成的视频"
   }
 }