Upload gradio_app.py

gradio_app.py

@@ -4,13 +4,13 @@ import asyncio
 import os
 
 # 定义生成音频的异步函数
-async def generate_audio(text, voice, rate, volume):
+async def generate_audio(text, voice, rate, volume, pitch):
     try:
         # 创建输出文件路径
         output_path = "output.mp3"
         
         # 使用edge-tts生成音频
-        communicate = edge_tts.Communicate(text, voice, rate=rate, volume=volume)
+        communicate = edge_tts.Communicate(text, voice, rate=rate, volume=volume, pitch=pitch)
         await communicate.save(output_path)
         
         return output_path
@@ -19,16 +19,17 @@ async def generate_audio(text, voice, rate, volume):
         raise gr.Error(f"生成音频失败: {str(e)}")
 
 # 定义Gradio界面的主函数
-def text_to_speech(text, voice, rate, volume):
+def text_to_speech(text, voice, rate, volume, pitch):
     try:
         # 将rate和volume参数转换为edge-tts需要的格式
         rate_str = f"+{int(rate)}%" if rate >= 0 else f"{int(rate)}%"
         volume_str = f"+{int(volume)}%" if volume >= 0 else f"{int(volume)}%"
+        pitch_str = f"+{int(pitch)}Hz" if pitch >= 0 else f"{int(pitch)}Hz"
         
         # 调用异步函数生成音频
         loop = asyncio.new_event_loop()
         asyncio.set_event_loop(loop)
-        output_path = loop.run_until_complete(generate_audio(text, voice, rate_str, volume_str))
+        output_path = loop.run_until_complete(generate_audio(text, voice, rate_str, volume_str, pitch_str))
         loop.close()
         
         return output_path
@@ -72,7 +73,7 @@ voice_options = get_voices()
 # 创建Gradio界面
 with gr.Blocks(title="Edge TTS 配音工具") as demo:
     gr.Markdown("# Edge TTS 配音工具")
-    gr.Markdown("输入文本，选择语音，调节语速和音量，然后点击合成按钮生成音频。")
+    gr.Markdown("输入文本，选择语音，调节语速、音量和语调，然后点击合成按钮生成音频。")
     
     with gr.Row():
         with gr.Column(scale=2):
@@ -111,6 +112,16 @@ with gr.Blocks(title="Edge TTS 配音工具") as demo:
                 info="-50% 到 +50%"
             )
             
+            # 语调滑块
+            pitch_slider = gr.Slider(
+                label="语调",
+                minimum=-50,
+                maximum=50,
+                step=5,
+                value=0,
+                info="-50Hz 到 +50Hz"
+            )
+            
             # 合成按钮
             generate_button = gr.Button("合成语音", variant="primary")
         
@@ -124,7 +135,7 @@ with gr.Blocks(title="Edge TTS 配音工具") as demo:
     # 设置按钮点击事件
     generate_button.click(
         fn=text_to_speech,
-        inputs=[text_input, voice_dropdown, rate_slider, volume_slider],
+        inputs=[text_input, voice_dropdown, rate_slider, volume_slider, pitch_slider],
         outputs=audio_output
     )