1. Added multi-language support to the UI

2. Optimized the voice name
3. Other UI optimizations

app/models/schema.py

@@ -34,43 +34,43 @@ class MaterialInfo:
     duration: int = 0
 
 
-VoiceNames = [
-    # zh-CN
-    "female-zh-CN-XiaoxiaoNeural",
-    "female-zh-CN-XiaoyiNeural",
-    "female-zh-CN-liaoning-XiaobeiNeural",
-    "female-zh-CN-shaanxi-XiaoniNeural",
-
-    "male-zh-CN-YunjianNeural",
-    "male-zh-CN-YunxiNeural",
-    "male-zh-CN-YunxiaNeural",
-    "male-zh-CN-YunyangNeural",
-
-    # "female-zh-HK-HiuGaaiNeural",
-    # "female-zh-HK-HiuMaanNeural",
-    # "male-zh-HK-WanLungNeural",
-    #
-    # "female-zh-TW-HsiaoChenNeural",
-    # "female-zh-TW-HsiaoYuNeural",
-    # "male-zh-TW-YunJheNeural",
-
-    # en-US
-
-    "female-en-US-AnaNeural",
-    "female-en-US-AriaNeural",
-    "female-en-US-AvaNeural",
-    "female-en-US-EmmaNeural",
-    "female-en-US-JennyNeural",
-    "female-en-US-MichelleNeural",
-
-    "male-en-US-AndrewNeural",
-    "male-en-US-BrianNeural",
-    "male-en-US-ChristopherNeural",
-    "male-en-US-EricNeural",
-    "male-en-US-GuyNeural",
-    "male-en-US-RogerNeural",
-    "male-en-US-SteffanNeural",
-]
+# VoiceNames = [
+#     # zh-CN
+#     "female-zh-CN-XiaoxiaoNeural",
+#     "female-zh-CN-XiaoyiNeural",
+#     "female-zh-CN-liaoning-XiaobeiNeural",
+#     "female-zh-CN-shaanxi-XiaoniNeural",
+#
+#     "male-zh-CN-YunjianNeural",
+#     "male-zh-CN-YunxiNeural",
+#     "male-zh-CN-YunxiaNeural",
+#     "male-zh-CN-YunyangNeural",
+#
+#     # "female-zh-HK-HiuGaaiNeural",
+#     # "female-zh-HK-HiuMaanNeural",
+#     # "male-zh-HK-WanLungNeural",
+#     #
+#     # "female-zh-TW-HsiaoChenNeural",
+#     # "female-zh-TW-HsiaoYuNeural",
+#     # "male-zh-TW-YunJheNeural",
+#
+#     # en-US
+#
+#     "female-en-US-AnaNeural",
+#     "female-en-US-AriaNeural",
+#     "female-en-US-AvaNeural",
+#     "female-en-US-EmmaNeural",
+#     "female-en-US-JennyNeural",
+#     "female-en-US-MichelleNeural",
+#
+#     "male-en-US-AndrewNeural",
+#     "male-en-US-BrianNeural",
+#     "male-en-US-ChristopherNeural",
+#     "male-en-US-EricNeural",
+#     "male-en-US-GuyNeural",
+#     "male-en-US-RogerNeural",
+#     "male-en-US-SteffanNeural",
+# ]
 
 
 class VideoParams:
@@ -97,7 +97,7 @@ class VideoParams:
 
     video_language: Optional[str] = ""  # auto detect
 
-    voice_name: Optional[str] = VoiceNames[0]
+    voice_name: Optional[str] = ""
     bgm_type: Optional[str] = "random"
     bgm_file: Optional[str] = ""
     bgm_volume: Optional[float] = 0.2

app/services/task.py

@@ -6,24 +6,11 @@ from os import path
 from loguru import logger
 
 from app.config import config
-from app.models.schema import VideoParams, VoiceNames, VideoConcatMode
+from app.models.schema import VideoParams, VideoConcatMode
 from app.services import llm, material, voice, video, subtitle
 from app.utils import utils
 
 
-def _parse_voice(name: str):
-    # "female-zh-CN-XiaoxiaoNeural",
-    # remove first part split by "-"
-    if name not in VoiceNames:
-        name = VoiceNames[0]
-
-    parts = name.split("-")
-    _lang = f"{parts[1]}-{parts[2]}"
-    _voice = f"{_lang}-{parts[3]}"
-
-    return _voice, _lang
-
-
 def start(task_id, params: VideoParams):
     """
     {
@@ -40,7 +27,7 @@ def start(task_id, params: VideoParams):
     """
     logger.info(f"start task: {task_id}")
     video_subject = params.video_subject
-    voice_name, language = _parse_voice(params.voice_name)
+    voice_name = voice.parse_voice_name(params.voice_name)
     paragraph_number = params.paragraph_number
     n_threads = params.n_threads
     max_clip_duration = params.video_clip_duration