Spaces:

Suryaboss
/

edge-tts

Sleeping

App Files Files Community

Suryaboss commited on Mar 22

Commit

91f7734

verified ·

1 Parent(s): 77136d7

Upload 4 files

Browse files

Files changed (4) hide show

Dockerfile +16 -0
index.html +94 -0
requirements.txt +3 -0
server.py +55 -0

Dockerfile ADDED Viewed

	@@ -0,0 +1,16 @@

+FROM python:3.10-slim
+WORKDIR /app
+# Install dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+# Copy the server files
+COPY . .
+# Hugging Face Spaces natively routes traffic on port 7860
+EXPOSE 7860
+# Start the FastAPI server using uvicorn mapped to the HF port
+CMD ["uvicorn", "server:app", "--host", "0.0.0.0", "--port", "7860"]

index.html ADDED Viewed

	@@ -0,0 +1,94 @@

+<!DOCTYPE html>
+<html>
+<head>
+    <title>Edge TTS Python Tester</title>
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <style>
+        body { font-family: system-ui, sans-serif; max-width: 600px; margin: 40px auto; padding: 20px; background: #fafafa; color: #333; }
+        .card { background: white; padding: 24px; border-radius: 12px; box-shadow: 0 4px 6px rgba(0,0,0,0.1); border: 1px solid #eaeaea; }
+        select, textarea, input { width: 100%; box-sizing: border-box; padding: 12px; margin: 8px 0 20px 0; border: 1px solid #ddd; border-radius: 6px; font-size: 15px; }
+        button { background: #0070f3; color: white; border: none; padding: 14px 24px; border-radius: 6px; cursor: pointer; width: 100%; font-weight: bold; font-size: 16px; transition: background 0.2s; }
+        button:hover { background: #0051b3; }
+        button:disabled { background: #ccc; cursor: not-allowed; }
+        audio { width: 100%; margin-top: 20px; border-radius: 8px; }
+        label { font-weight: 600; font-size: 14px; }
+    </style>
+</head>
+<body>
+    <div class="card">
+        <h2 style="margin-top: 0; text-align: center;">🎙️ Edge TTS Native Tester</h2>
+        <label>API Server URL (leave blank for auto-detect):</label>
+        <input type="text" id="serverUrl" placeholder="http://localhost:8000" value="">
+        <label>Select Neural Voice:</label>
+        <select id="voiceId">
+            <option value="en-US-JennyNeural">Jenny (US English - Female)</option>
+            <option value="en-US-GuyNeural">Guy (US English - Male)</option>
+            <option value="hi-IN-SwaraNeural" selected>Swara (Hindi - Female)</option>
+            <option value="hi-IN-MadhurNeural">Madhur (Hindi - Male)</option>
+            <option value="en-IN-NeerjaNeural">Neerja (Indian English - Female)</option>
+            <option value="en-IN-PrabhatNeural">Prabhat (Indian English - Male)</option>
+        </select>
+        <label>Text to Synthesize:</label>
+        <textarea id="text" rows="4">नमस्ते! मैं माइक्रोसॉफ्ट एज टीटीएस का परीक्षण कर रही हूं।</textarea>
+        <button onclick="generateAudio()" id="genBtn">Generate Speech</button>
+        <div id="status" style="margin-top: 15px; color: #666; font-size: 14px; text-align: center;">Ready. Click Generate to test the Proxy.</div>
+        <audio id="audioPlayer" controls style="display: none;"></audio>
+    </div>
+    <script>
+        async function generateAudio() {
+            const btn = document.getElementById('genBtn');
+            const statusBox = document.getElementById('status');
+            const audio = document.getElementById('audioPlayer');
+            let baseUrl = document.getElementById('serverUrl').value.trim() || window.location.origin;
+            // If running as local file directly without a server, fallback to default port 8000
+            if (baseUrl === "null" || baseUrl.startsWith("file://")) baseUrl = "http://localhost:8000";
+            const text = encodeURIComponent(document.getElementById('text').value);
+            const voice = encodeURIComponent(document.getElementById('voiceId').value);
+            btn.disabled = true;
+            btn.innerText = "Synthesizing...";
+            statusBox.style.color = "#666";
+            statusBox.innerText = `Routing request to ${baseUrl}...`;
+            audio.style.display = "none";
+            try {
+                // The API endpoint we built is GET /tts?text=...&voice=...
+                const url = `${baseUrl}/tts?text=${text}&voice=${voice}&rate=%2B0%25`;
+                statusBox.innerText = `Establishing fast socket to Microsoft Edge...`;
+                const response = await fetch(url);
+                if (!response.ok) {
+                    const errorText = await response.text();
+                    throw new Error(`Server Error ${response.status}: ${errorText}`);
+                }
+                // Construct a playable Object URL directly from the raw mp3 blob
+                const blob = await response.blob();
+                const blobUrl = URL.createObjectURL(blob);
+                audio.src = blobUrl;
+                audio.style.display = "block";
+                audio.play();
+                statusBox.innerText = "✅ Success! Edge TTS generated without 403 Ban.";
+                statusBox.style.color = "green";
+            } catch (error) {
+                console.error(error);
+                statusBox.innerText = "❌ Error: " + error.message;
+                statusBox.style.color = "red";
+            } finally {
+                btn.disabled = false;
+                btn.innerText = "Generate Speech";
+            }
+        }
+    </script>
+</body>
+</html>

requirements.txt ADDED Viewed

	@@ -0,0 +1,3 @@

+fastapi==0.115.6
+uvicorn==0.34.0
+edge-tts==6.6.1

server.py ADDED Viewed

	@@ -0,0 +1,55 @@

+from fastapi import FastAPI, Response, HTTPException
+from fastapi.responses import HTMLResponse
+from fastapi.middleware.cors import CORSMiddleware
+import edge_tts
+import tempfile
+import os
+app = FastAPI()
+# Allow CORS for Next.js to call directly or Server-to-Server
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+@app.get("/")
+def read_root():
+    # Automatically serve the HTML Tester UI if it exists alongside the server script
+    html_path = os.path.join(os.path.dirname(__file__), "index.html")
+    if os.path.exists(html_path):
+        with open(html_path, "r", encoding="utf-8") as f:
+            return HTMLResponse(content=f.read())
+    return {"status": "Edge TTS Proxy is running securely"}
+@app.get("/tts")
+async def generate_tts(text: str, voice: str = "en-US-JennyNeural", rate: str = "+0%"):
+    if not text:
+        raise HTTPException(status_code=400, detail="Missing text parameter")
+    try:
+        # edge-tts python library natively bypasses 403 API IP Bans automatically!
+        communicate = edge_tts.Communicate(text, voice, rate=rate)
+        with tempfile.NamedTemporaryFile(suffix=".mp3", delete=False) as fp:
+            temp_path = fp.name
+        await communicate.save(temp_path)
+        with open(temp_path, "rb") as f:
+            audio_data = f.read()
+        os.remove(temp_path)
+        return Response(content=audio_data, media_type="audio/mpeg")
+    except Exception as e:
+        print(f"Server Error during TTS synthesis: {e}")
+        raise HTTPException(status_code=500, detail=str(e))
+if __name__ == "__main__":
+    import uvicorn
+    # Important: Cloud hosts like Render inject the dynamic port into PORT env var
+    port = int(os.environ.get("PORT", 8000))
+    uvicorn.run(app, host="0.0.0.0", port=port)