Upload 8 files

app.py

@@ -0,0 +1,60 @@
+from fastapi import FastAPI, HTTPException
+from fastapi.responses import StreamingResponse
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+import edge_tts
+import asyncio
+
+app = FastAPI(title="Edge TTS API", description="基于Edge TTS的文本转语音API", version="1.0")
+
+# 添加CORS支持
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # 允许所有来源，生产环境中应限制为特定域名
+    allow_credentials=True,
+    allow_methods=["*"],  # 允许所有HTTP方法
+    allow_headers=["*"],  # 允许所有HTTP头
+)
+
+class TTSRequest(BaseModel):
+    text: str
+    voice: str = "zh-CN-YunxiNeural"
+    rate: str = "+0%"
+    volume: str = "+0%"
+
+@app.post("/tts", response_class=StreamingResponse, summary="文本转语音")
+async def text_to_speech(request: TTSRequest):
+    try:
+        communicate = edge_tts.Communicate(request.text, request.voice, rate=request.rate, volume=request.volume)
+        
+        # 先将所有音频数据收集到内存中
+        audio_data = b""
+        async for chunk in communicate.stream():
+            if chunk["type"] == "audio":
+                audio_data += chunk["data"]
+        
+        # 然后返回完整的音频数据
+        return StreamingResponse(iter([audio_data]), media_type="audio/mpeg")
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.get("/voices", summary="获取可用语音列表")
+async def get_voices():
+    try:
+        voices = await edge_tts.list_voices()
+        return [{
+            "short_name": voice.get("ShortName", ""),
+            "friendly_name": voice.get("FriendlyName", voice.get("ShortName", "")),
+            "gender": voice.get("Gender", ""),
+            "locale": voice.get("Locale", "")
+        } for voice in voices]
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.get("/", summary="首页")
+def read_root():
+    return {"message": "欢迎使用Edge TTS API", "docs": "/docs"}
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=7860)

check_hf_space.py

@@ -0,0 +1,48 @@
+import requests
+
+# 检查Space的文件结构
+def check_space_files():
+    print("检查Hugging Face Space的文件结构...")
+    url = "https://huggingface.co/api/spaces/chaore/ttsedge/files"
+    
+    try:
+        response = requests.get(url)
+        if response.status_code == 200:
+            files = response.json()
+            print(f"Space中包含 {len(files)} 个文件:")
+            for file in files:
+                print(f"  - {file['path']} (大小: {file.get('size', '未知')} 字节)")
+            return True
+        else:
+            print(f"获取文件列表失败: {response.status_code}")
+            print(f"响应内容: {response.text}")
+            return False
+    except Exception as e:
+        print(f"检查文件结构时出错: {e}")
+        return False
+
+# 检查Space的状态
+def check_space_status():
+    print("\n检查Space的状态...")
+    url = "https://huggingface.co/api/spaces/chaore/ttsedge"
+    
+    try:
+        response = requests.get(url)
+        if response.status_code == 200:
+            space_info = response.json()
+            print(f"Space名称: {space_info['name']}")
+            print(f"作者: {space_info['author']}")
+            print(f"状态: {space_info['status']}")
+            print(f"最后更新: {space_info['lastModified']}")
+            print(f"可见性: {space_info['private']}")
+            return True
+        else:
+            print(f"获取Space信息失败: {response.status_code}")
+            return False
+    except Exception as e:
+        print(f"检查Space状态时出错: {e}")
+        return False
+
+if __name__ == "__main__":
+    check_space_files()
+    check_space_status()

gradio_app.py

@@ -0,0 +1,111 @@
+import gradio as gr
+import edge_tts
+import asyncio
+import os
+
+# 定义生成音频的异步函数
+async def generate_audio(text, voice, rate, volume):
+    # 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)
+    await communicate.save(output_path)
+    
+    return output_path
+
+# 定义Gradio界面的主函数
+def text_to_speech(text, voice, rate, volume):
+    # 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, volume))
+    loop.close()
+    
+    return output_path
+
+# 异步获取所有可用语音
+def get_voices():
+    loop = asyncio.new_event_loop()
+    asyncio.set_event_loop(loop)
+    voices = loop.run_until_complete(edge_tts.list_voices())
+    loop.close()
+    
+    # 过滤出支持的语音，并按语言分组
+    voice_options = []
+    for voice in voices:
+        short_name = voice.get("ShortName", "")
+        friendly_name = voice.get("FriendlyName", short_name)
+        locale = voice.get("Locale", "")
+        voice_options.append((f"{friendly_name} ({locale})", short_name))
+    
+    # 按友好名称排序
+    voice_options.sort(key=lambda x: x[0])
+    
+    return voice_options
+
+# 获取所有可用语音
+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。")
+    
+    with gr.Row():
+        with gr.Column(scale=2):
+            # 文本输入框
+            text_input = gr.Textbox(
+                label="输入文本",
+                placeholder="请输入要转换为语音的文本...",
+                lines=5,
+                max_lines=10
+            )
+            
+            # 语音选择下拉菜单
+            voice_dropdown = gr.Dropdown(
+                label="选择语音",
+                choices=voice_options,
+                value="zh-CN-YunxiNeural"
+            )
+            
+            # 语速滑块
+            rate_slider = gr.Slider(
+                label="语速",
+                minimum=-50,
+                maximum=50,
+                step=5,
+                value=0,
+                info="-50% 到 +50%"
+            )
+            
+            # 音量滑块
+            volume_slider = gr.Slider(
+                label="音量",
+                minimum=-50,
+                maximum=50,
+                step=5,
+                value=0,
+                info="-50% 到 +50%"
+            )
+            
+            # 合成按钮
+            generate_button = gr.Button("合成语音", variant="primary")
+        
+        with gr.Column(scale=1):
+            # 音频输出
+            audio_output = gr.Audio(
+                label="合成音频",
+                type="filepath"
+            )
+    
+    # 设置按钮点击事件
+    generate_button.click(
+        fn=text_to_speech,
+        inputs=[text_input, voice_dropdown, rate_slider, volume_slider],
+        outputs=audio_output
+    )
+
+# 启动Gradio应用
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860)

requirements.txt

@@ -0,0 +1,5 @@
+edge-tts
+fastapi
+uvicorn
+python-multipart
+gradio

test_edge_tts.py

@@ -0,0 +1,44 @@
+import edge_tts
+import asyncio
+
+async def test_edge_tts():
+    print("测试Edge TTS库...")
+    try:
+        # 测试列出语音
+        voices = await edge_tts.list_voices()
+        print(f"获取到 {len(voices)} 种语音")
+        
+        # 测试语音合成
+        text = "Welcome to Edge TTS"
+        voice = "en-US-JennyNeural"
+        
+        print(f"\n正在合成语音: {text}")
+        print(f"使用语音: {voice}")
+        
+        communicate = edge_tts.Communicate(text, voice)
+        audio_data = b""
+        
+        async for chunk in communicate.stream():
+            if chunk["type"] == "audio":
+                audio_data += chunk["data"]
+            elif chunk["type"] == "WordBoundary":
+                print(f"\r正在处理: {chunk['text']}", end="")
+        
+        if audio_data:
+            print(f"\n\n语音合成成功，音频大小: {len(audio_data)} 字节")
+            with open("direct_edge_tts.mp3", "wb") as f:
+                f.write(audio_data)
+            print("音频已保存为 direct_edge_tts.mp3")
+            return True
+        else:
+            print("\n\n错误: 没有获取到音频数据")
+            return False
+            
+    except Exception as e:
+        print(f"\n\n错误: {e}")
+        import traceback
+        traceback.print_exc()
+        return False
+
+if __name__ == "__main__":
+    asyncio.run(test_edge_tts())

test_tts.py

@@ -0,0 +1,46 @@
+import requests
+import json
+
+# 测试获取语音列表
+def test_voices():
+    print("测试获取语音列表...")
+    response = requests.get("http://localhost:7860/voices")
+    if response.status_code == 200:
+        voices = response.json()
+        print(f"获取到 {len(voices)} 种语音")
+        # 打印前5种中文语音
+        print("中文语音示例：")
+        chinese_voices = [v for v in voices if v['locale'].startswith('zh-')]
+        for voice in chinese_voices[:5]:
+            print(f"  - {voice['friendly_name']} ({voice['short_name']})")
+        return True
+    else:
+        print(f"获取语音列表失败: {response.status_code}")
+        return False
+
+# 测试文本转语音
+def test_tts():
+    print("\n测试文本转语音...")
+    text = "欢迎使用Edge TTS API服务，这是一个测试语音。"
+    payload = {
+        "text": text,
+        "voice": "zh-CN-YunxiNeural",
+        "rate": "+0%",
+        "volume": "+0%"
+    }
+    response = requests.post("http://localhost:7860/tts", json=payload, stream=True)
+    if response.status_code == 200:
+        with open("test_output.mp3", "wb") as f:
+            for chunk in response.iter_content(chunk_size=1024):
+                if chunk:
+                    f.write(chunk)
+        print("语音合成成功，已保存为 test_output.mp3")
+        return True
+    else:
+        print(f"语音合成失败: {response.status_code}")
+        print(f"错误信息: {response.text}")
+        return False
+
+if __name__ == "__main__":
+    test_voices()
+    test_tts()