Spaces:

eshwar06
/

piper-tts-server

Build error

App Files Files Community

eshwar06 commited on Sep 25, 2025

Commit

115cdc4

verified ·

1 Parent(s): 933d51f

Update app.py

Browse files

Files changed (1) hide show

app.py +238 -252

app.py CHANGED Viewed

@@ -1,28 +1,21 @@
-# app.py - FastAPI + Gradio for Hugging Face Spaces
 import os
-import asyncio
 import logging
 import tempfile
 import subprocess
 from pathlib import Path
-from typing import Optional
 import requests
-import json
-import threading
-import time
-import gradio as gr
-from fastapi import FastAPI, HTTPException
-from fastapi.responses import FileResponse
-from fastapi.middleware.cors import CORSMiddleware
 import uvicorn
 # Configure logging
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 class PiperTTSSpaces:
-    """Piper TTS optimized for Hugging Face Spaces with FastAPI"""
     def __init__(self):
         self.model_path = self._setup_model()
@@ -75,7 +68,7 @@ class PiperTTSSpaces:
                 "--output_file", temp_file.name
             ]
-            logger.info(f"Running: {' '.join(cmd)}")
             # Run Piper with text input
             process = subprocess.run(
@@ -124,8 +117,221 @@ app.add_middleware(
     allow_headers=["*"],
 )
 @app.post("/api/tts")
-async def api_generate_tts(request: dict):
     """
     Generate TTS from text
@@ -144,7 +350,6 @@ async def api_generate_tts(request: dict):
         raise HTTPException(status_code=503, detail="TTS engine not available")
     try:
-        logger.info(f"API TTS request: '{text[:50]}...'")
         audio_file = tts_engine.synthesize_to_file(text)
         return FileResponse(
@@ -155,7 +360,7 @@ async def api_generate_tts(request: dict):
         )
     except Exception as e:
-        logger.error(f"API TTS failed: {e}")
         raise HTTPException(status_code=500, detail=str(e))
 @app.get("/api/health")
@@ -164,245 +369,26 @@ async def health_check():
     return {
         "status": "healthy" if tts_engine else "tts_engine_unavailable",
         "service": "Piper TTS",
-        "model_loaded": tts_engine is not None
     }
-@app.get("/")
-async def root():
-    """Root endpoint - redirects to Gradio interface"""
-    return {"message": "Piper TTS API is running. Visit /docs for API documentation."}
-# Gradio interface functions
-def generate_speech(text, progress=gr.Progress()):
-    """Generate speech from text for Gradio"""
-    if not text or not text.strip():
-        return None, "⚠️ Please enter some text to convert to speech."
-    if tts_engine is None:
-        return None, "❌ TTS engine not available. Please check the logs."
-    if len(text) > 1000:
-        return None, "⚠️ Text is too long. Please limit to 1000 characters."
-    try:
-        progress(0.2, desc="Initializing TTS...")
-        progress(0.5, desc="Generating speech...")
-        audio_file = tts_engine.synthesize_to_file(text)
-        progress(0.9, desc="Finalizing...")
-        progress(1.0, desc="Complete!")
-        success_msg = f"✅ Generated speech for: '{text[:50]}{'...' if len(text) > 50 else ''}'"
-        return audio_file, success_msg
-    except Exception as e:
-        error_msg = f"❌ Error generating speech: {str(e)}"
-        logger.error(error_msg)
-        return None, error_msg
-def clear_inputs():
-    """Clear all inputs and outputs"""
-    return "", None, "Ready for new text..."
-# Create Gradio interface
-def create_gradio_interface():
-    """Create the Gradio interface"""
-    css = """
-    .container { max-width: 900px; margin: auto; }
-    .header { text-align: center; margin-bottom: 2rem; }
-    .example-btn { margin: 0.25rem; }
-    .status-box { border-radius: 8px; }
-    """
-    with gr.Blocks(
-        theme=gr.themes.Soft(),
-        title="🎙️ Piper TTS with FastAPI",
-        css=css
-    ) as interface:
-        gr.Markdown(
-            """
-            # 🎙️ Piper TTS with FastAPI Integration
-            High-quality neural text-to-speech with **both Gradio UI and FastAPI endpoints**.
-            Perfect for digital companions and conversational AI applications.
-            ✨ **Features:**
-            - 🌐 **FastAPI Endpoints** for easy integration
-            - 🎯 **Gradio Interface** for testing
-            - ⚡ **Low Latency** neural synthesis
-            - 🔄 **Production Ready** with proper CORS
-            """,
-            elem_classes=["header"]
-        )
-        with gr.Row():
-            with gr.Column(scale=2):
-                text_input = gr.Textbox(
-                    label="💬 Text to Convert",
-                    placeholder="Enter the text you want to convert to speech...",
-                    lines=4,
-                    max_lines=8,
-                    value="Hello! I'm your digital companion with FastAPI integration."
-                )
-                with gr.Row():
-                    generate_btn = gr.Button("🎵 Generate Speech", variant="primary", size="lg")
-                    clear_btn = gr.Button("🗑️ Clear", variant="secondary")
-            with gr.Column(scale=1):
-                gr.Markdown("### 📝 Quick Examples")
-                examples = [
-                    "Hello! How can I help you today?",
-                    "I'm excited to assist with your questions.",
-                    "Thank you for using our TTS service!",
-                    "The API is working perfectly!",
-                    "I understand what you're asking about.",
-                    "Let me process that information."
-                ]
-            for example in examples:
-                label = f"{example[:35]}{'...' if len(example) > 35 else ''}"
-                example_btn = gr.Button(
-                 label,
-                 size="sm",
-                  elem_classes=["example-btn"]
-            )
-        example_btn.click(lambda x=example: x, outputs=text_input)
-        # Output section
-        with gr.Row():
-            audio_output = gr.Audio(
-                label="🔊 Generated Speech",
-                type="filepath",
-                autoplay=True,
-                show_download_button=True
-            )
-        status_output = gr.Textbox(
-            label="📊 Status",
-            interactive=False,
-            value="Ready! Use either the interface above OR the FastAPI endpoints.",
-            elem_classes=["status-box"]
-        )
-        # API Documentation
-        with gr.Accordion("🚀 FastAPI Integration", open=True):
-            gr.Markdown(
-                """
-                ### 🌐 REST API Endpoints
-                **Your Space provides these FastAPI endpoints:**
-                #### Generate TTS
-                ```bash
-                curl -X POST "https://eshwar06-piper-tts-server.hf.space/api/tts" \\
-                     -H "Content-Type: application/json" \\
-                     -d '{"text": "Hello from FastAPI!"}' \\
-                     --output speech.wav
-                ```
-                #### Health Check
-                ```bash
-                curl "https://eshwar06-piper-tts-server.hf.space/api/health"
-                ```
-                #### Python Usage
-                ```python
-                import requests
-                # Generate TTS
-                response = requests.post(
-                    "https://eshwar06-piper-tts-server.hf.space/api/tts",
-                    json={"text": "Hello from Python!"}
-                )
-                # Save audio
-                with open("speech.wav", "wb") as f:
-                    f.write(response.content)
-                ```
-                #### For Your Digital Companion
-                ```python
-                import requests
-                class DigitalCompanion:
-                    def __init__(self):
-                        self.tts_url = "https://eshwar06-piper-tts-server.hf.space/api/tts"
-                    def speak(self, text):
-                        response = requests.post(
-                            self.tts_url,
-                            json={"text": text}
-                        )
-                        return response.content  # WAV audio bytes
-                # Usage
-                companion = DigitalCompanion()
-                audio_data = companion.speak("I'm your AI assistant!")
-                ```
-                ### 📋 API Documentation
-                Visit: `https://eshwar06-piper-tts-server.hf.space/docs` for interactive API docs!
-                """
-            )
-        # Event handlers
-        generate_btn.click(
-            fn=generate_speech,
-            inputs=[text_input],
-            outputs=[audio_output, status_output],
-            show_progress="full"
-        )
-        clear_btn.click(
-            fn=clear_inputs,
-            outputs=[text_input, audio_output, status_output]
-        )
-        text_input.submit(
-            fn=generate_speech,
-            inputs=[text_input],
-            outputs=[audio_output, status_output],
-            show_progress="full"
-        )
-        gr.Markdown(
-            """
-            ---
-            🌐 **FastAPI Integration Ready!** Use `/api/tts` for your applications.
-            📚 **API Docs:** Visit `/docs` for interactive documentation.
-            ⭐ **Perfect for Digital Companions** with low-latency TTS.
-            """,
-            elem_classes=["header"]
-        )
-    return interface
-# Create Gradio interface
-gradio_app = create_gradio_interface()
-def run_fastapi():
-    """Run FastAPI server in a separate thread"""
-    uvicorn.run(app, host="0.0.0.0", port=7861, log_level="warning")
-# Start FastAPI in background thread
 if __name__ == "__main__":
-    # Start FastAPI server in background
-    fastapi_thread = threading.Thread(target=run_fastapi, daemon=True)
-    fastapi_thread.start()
-    # Give FastAPI time to start
-    time.sleep(2)
-    # Launch Gradio (main process)
-    gradio_app.launch(
-        server_name="0.0.0.0",
-        server_port=7860,
-        show_error=True,
-        share=False
     )

+# app.py - Simple FastAPI-only version for Hugging Face Spaces
 import os
 import logging
 import tempfile
 import subprocess
 from pathlib import Path
 import requests
 import uvicorn
+from fastapi import FastAPI, HTTPException, Request
+from fastapi.responses import FileResponse, HTMLResponse
+from fastapi.middleware.cors import CORSMiddleware
 # Configure logging
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 class PiperTTSSpaces:
+    """Piper TTS for Hugging Face Spaces with FastAPI"""
     def __init__(self):
         self.model_path = self._setup_model()
                 "--output_file", temp_file.name
             ]
+            logger.info(f"TTS request: '{text[:50]}...'")
             # Run Piper with text input
             process = subprocess.run(
     allow_headers=["*"],
 )
+@app.get("/", response_class=HTMLResponse)
+async def root():
+    """Serve a simple HTML interface"""
+    return HTMLResponse("""
+    <!DOCTYPE html>
+    <html>
+    <head>
+        <title>🎙️ Piper TTS API</title>
+        <meta charset="UTF-8">
+        <meta name="viewport" content="width=device-width, initial-scale=1.0">
+        <style>
+            body {
+                font-family: -apple-system, BlinkMacSystemFont, sans-serif;
+                max-width: 800px;
+                margin: 0 auto;
+                padding: 20px;
+                background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+                min-height: 100vh;
+                color: white;
+            }
+            .container {
+                background: rgba(255, 255, 255, 0.1);
+                padding: 30px;
+                border-radius: 15px;
+                backdrop-filter: blur(10px);
+                box-shadow: 0 8px 32px rgba(31, 38, 135, 0.37);
+            }
+            .header { text-align: center; margin-bottom: 30px; }
+            .form-group { margin: 20px 0; }
+            label { display: block; margin-bottom: 8px; font-weight: bold; }
+            textarea {
+                width: 100%;
+                padding: 12px;
+                border: none;
+                border-radius: 8px;
+                font-size: 16px;
+                background: rgba(255, 255, 255, 0.9);
+                color: #333;
+                resize: vertical;
+            }
+            button {
+                background: #4CAF50;
+                color: white;
+                padding: 12px 24px;
+                border: none;
+                border-radius: 8px;
+                font-size: 16px;
+                cursor: pointer;
+                margin: 5px;
+            }
+            button:hover { background: #45a049; }
+            button:disabled { background: #cccccc; cursor: not-allowed; }
+            .status {
+                margin: 15px 0;
+                padding: 10px;
+                border-radius: 5px;
+                background: rgba(255, 255, 255, 0.1);
+            }
+            .success { background: rgba(76, 175, 80, 0.3); }
+            .error { background: rgba(244, 67, 54, 0.3); }
+            audio { width: 100%; margin: 10px 0; }
+            .examples {
+                display: grid;
+                grid-template-columns: repeat(auto-fit, minmax(200px, 1fr));
+                gap: 10px;
+                margin: 20px 0;
+            }
+            .example-btn {
+                background: rgba(255, 255, 255, 0.2);
+                padding: 8px 12px;
+                font-size: 14px;
+            }
+            .api-info {
+                background: rgba(0, 0, 0, 0.2);
+                padding: 20px;
+                border-radius: 10px;
+                margin: 20px 0;
+            }
+            code {
+                background: rgba(0, 0, 0, 0.3);
+                padding: 2px 6px;
+                border-radius: 4px;
+                font-family: monospace;
+            }
+        </style>
+    </head>
+    <body>
+        <div class="container">
+            <div class="header">
+                <h1>🎙️ Piper TTS API</h1>
+                <p>High-quality neural text-to-speech for digital companions</p>
+            </div>
+            <div class="form-group">
+                <label for="textInput">💬 Enter text to convert to speech:</label>
+                <textarea id="textInput" rows="4" placeholder="Hello! I'm your digital companion powered by Piper TTS.">Hello! I'm your digital companion powered by Piper TTS. I can generate natural-sounding speech perfect for conversational AI applications.</textarea>
+            </div>
+            <div class="form-group">
+                <button onclick="generateSpeech()" id="generateBtn">🎵 Generate Speech</button>
+                <button onclick="clearAll()">🗑️ Clear</button>
+            </div>
+            <div class="examples">
+                <button class="example-btn" onclick="setExample('Hello! How can I help you today?')">Greeting</button>
+                <button class="example-btn" onclick="setExample('I understand your question perfectly.')">Understanding</button>
+                <button class="example-btn" onclick="setExample('Let me think about that for a moment.')">Thinking</button>
+                <button class="example-btn" onclick="setExample('Thank you for using our service!')">Thanks</button>
+                <button class="example-btn" onclick="setExample('Is there anything else you need help with?')">Follow-up</button>
+                <button class="example-btn" onclick="setExample('I apologize for any confusion.')">Apology</button>
+            </div>
+            <div id="status" class="status" style="display: none;"></div>
+            <audio id="audioPlayer" controls style="display: none;"></audio>
+            <div class="api-info">
+                <h3>🚀 API Integration</h3>
+                <p><strong>Endpoint:</strong> <code>POST /api/tts</code></p>
+                <p><strong>Body:</strong> <code>{"text": "Your text here"}</code></p>
+                <p><strong>Response:</strong> WAV audio file</p>
+                <h4>Python Example:</h4>
+                <pre><code>import requests
+response = requests.post(
+    "https://eshwar06-piper-tts-server.hf.space/api/tts",
+    json={"text": "Hello from Python!"}
+)
+with open("speech.wav", "wb") as f:
+    f.write(response.content)</code></pre>
+                <h4>cURL Example:</h4>
+                <pre><code>curl -X POST "https://eshwar06-piper-tts-server.hf.space/api/tts" \\
+     -H "Content-Type: application/json" \\
+     -d '{"text":"Hello world!"}' \\
+     --output speech.wav</code></pre>
+            </div>
+        </div>
+        <script>
+            function setExample(text) {
+                document.getElementById('textInput').value = text;
+            }
+            function clearAll() {
+                document.getElementById('textInput').value = '';
+                document.getElementById('status').style.display = 'none';
+                document.getElementById('audioPlayer').style.display = 'none';
+            }
+            async function generateSpeech() {
+                const text = document.getElementById('textInput').value;
+                const statusDiv = document.getElementById('status');
+                const audioPlayer = document.getElementById('audioPlayer');
+                const generateBtn = document.getElementById('generateBtn');
+                if (!text.trim()) {
+                    showStatus('Please enter some text', 'error');
+                    return;
+                }
+                generateBtn.disabled = true;
+                generateBtn.textContent = '⏳ Generating...';
+                showStatus('Generating speech, please wait...', 'info');
+                try {
+                    const response = await fetch('/api/tts', {
+                        method: 'POST',
+                        headers: {
+                            'Content-Type': 'application/json',
+                        },
+                        body: JSON.stringify({text: text})
+                    });
+                    if (response.ok) {
+                        const audioBlob = await response.blob();
+                        const audioUrl = URL.createObjectURL(audioBlob);
+                        audioPlayer.src = audioUrl;
+                        audioPlayer.style.display = 'block';
+                        showStatus('✅ Speech generated successfully! Click play below.', 'success');
+                    } else {
+                        const errorText = await response.text();
+                        showStatus(`❌ Error: ${response.status} - ${errorText}`, 'error');
+                    }
+                } catch (error) {
+                    showStatus(`❌ Error: ${error.message}`, 'error');
+                } finally {
+                    generateBtn.disabled = false;
+                    generateBtn.textContent = '🎵 Generate Speech';
+                }
+            }
+            function showStatus(message, type) {
+                const statusDiv = document.getElementById('status');
+                statusDiv.textContent = message;
+                statusDiv.className = `status ${type}`;
+                statusDiv.style.display = 'block';
+            }
+            // Allow Enter key to generate speech
+            document.getElementById('textInput').addEventListener('keypress', function(e) {
+                if (e.key === 'Enter' && e.ctrlKey) {
+                    generateSpeech();
+                }
+            });
+        </script>
+    </body>
+    </html>
+    """)
 @app.post("/api/tts")
+async def generate_tts(request: dict):
     """
     Generate TTS from text
         raise HTTPException(status_code=503, detail="TTS engine not available")
     try:
         audio_file = tts_engine.synthesize_to_file(text)
         return FileResponse(
         )
     except Exception as e:
+        logger.error(f"TTS failed: {e}")
         raise HTTPException(status_code=500, detail=str(e))
 @app.get("/api/health")
     return {
         "status": "healthy" if tts_engine else "tts_engine_unavailable",
         "service": "Piper TTS",
+        "model_loaded": tts_engine is not None,
+        "version": "1.0.0"
     }
+@app.get("/docs-redirect")
+async def docs_redirect():
+    """Redirect to API docs"""
+    return {"message": "Visit /docs for interactive API documentation"}
+# Health check for Spaces
+@app.get("/health")
+async def health_alias():
+    """Alternative health endpoint"""
+    return await health_check()
 if __name__ == "__main__":
+    # Run the FastAPI app
+    uvicorn.run(
+        app,
+        host="0.0.0.0",
+        port=7860,  # Spaces default port
+        log_level="info"
     )