Simplify: Remove Supabase, auth, and quotas - pure TTS API

.env.example

@@ -1,10 +1,2 @@
-# Supabase Configuration
-# Copy this file to .env and fill in your actual values
-# For Hugging Face Spaces, add these as Secrets in the Space settings
-
-SUPABASE_URL=http://supabasekong-ggosk0kkwsw8swcwsooo8o48.16.170.15.157.sslip.io
-SUPABASE_KEY=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJzdXBhYmFzZSIsImlhdCI6MTc2MzYzNDg0MCwiZXhwIjo0OTE5MzA4NDQwLCJyb2xlIjoiYW5vbiJ9.73mWaXstDrk1wQGYaWMSi2-GWSb4_MvOXMwtM96sjCI
-
-# Admin Credentials (Optional - defaults are set in app.py)
-# ADMIN_USERNAME=admin
-# ADMIN_PASSWORD=your_secure_password
+# No environment variables needed!
+# This TTS service runs without authentication or database

README.md

@@ -1,5 +1,5 @@
 ---
-title: Kokoro TTS API - Professional & Fast
+title: Kokoro TTS API - Simple & Fast
 emoji: 🎤
 colorFrom: blue
 colorTo: purple
@@ -8,125 +8,122 @@ app_file: app.py
 pinned: false
 ---
 
-# Kokoro TTS Service - Professional & Lightning Fast ⚡
+# 🎤 Kokoro TTS API - Simple & Fast
 
-**10x faster than XTTS** | Emotional voices for storytelling | CPU-optimized
+High-speed text-to-speech service powered by Kokoro (82M parameters). No authentication, no database - just pure TTS!
 
-## 🚀 Why Kokoro?
+## ⚡ Features
 
-- ⚡ **Lightning Fast**: Generates audio in real-time on CPU
-- 🎭 **Emotional Expression**: Perfect for audiobooks & storytelling
-- 💾 **Lightweight**: Only 82M parameters (vs XTTS 400M+)
-- 🔒 **Secure**: Supabase authentication with user management
-- 📊 **High Quota**: 50 generations/day (vs 3 with XTTS)
+- **Lightning Fast**: 10x faster than XTTS
+- **Emotional Voices**: 6 expressive voices
+- **CPU Optimized**: Runs smoothly on CPU
+- **No Auth Required**: Simple HTTP API
+- **Long Audio**: Up to 5 minutes per generation
 
-## 🔐 Admin Credentials
-```
-Username: madhab
-Password: Madhab@Studify2024!
-```
-
-## 📦 Setup
-
-### 1. Supabase Database
-Run `supabase_schema.sql` in your Supabase SQL Editor
-
-### 2. Install & Run
-```bash
-pip install -r requirements.txt
-python app.py
-```
-
-## 🎤 Available Voices
+## 🎵 Available Voices
 
 | Voice | Description | Best For |
 |-------|-------------|----------|
-| `af_heart` | American Female (warm) | General narration |
-| `af_bella` | American Female (professional) | Educational content |
-| `am_adam` | American Male (confident) | Business/Tech |
-| `am_michael` | American Male (friendly) | Casual/Conversational |
-| `bf_emma` | British Female (elegant) | Formal content |
-| `bf_isabella` | British Female (storytelling) | **Audiobooks/Stories** ⭐ |
+| `bf_isabella` | British Female | ⭐ Storytelling, audiobooks |
+| `af_heart` | American Female | Warm, conversational |
+| `af_bella` | American Female | Professional narration |
+| `bf_emma` | British Female | Elegant, formal |
+| `am_adam` | American Male | Confident, clear |
+| `am_michael` | American Male | Friendly, casual |
+
+## 🚀 Quick Start
 
-## 📡 API Usage
+### Using curl:
 
-### Generate Speech (Fast!)
 ```bash
-curl -X POST http://localhost:7860/api/generate \
-  -F "username=madhab" \
-  -F "password=Madhab@Studify2024!" \
-  -F "text=The concept of artificial intelligence has evolved significantly over the past few decades." \
+curl -X POST https://your-space.hf.space/api/generate \
+  -F "text=Once upon a time, in a distant kingdom..." \
   -F "voice=bf_isabella" \
   -F "speed=1.0" \
-  --output output.wav
+  --output story.wav
 ```
 
-### Check Quota
-```bash
-curl -X POST http://localhost:7860/api/quota \
-  -F "username=madhab" \
-  -F "password=Madhab@Studify2024!"
+### Using Python:
+
+```python
+import requests
+
+response = requests.post(
+    "https://your-space.hf.space/api/generate",
+    data={
+        "text": "Hello world! This is Kokoro TTS.",
+        "voice": "bf_isabella",
+        "speed": 1.0
+    }
+)
+
+with open("audio.wav", "wb") as f:
+    f.write(response.content)
 ```
 
-### Create New User (Admin)
-```bash
-curl -X POST http://localhost:7860/api/admin/create-user \
-  -F "admin_username=madhab" \
-  -F "admin_password=Madhab@Studify2024!" \
-  -F "new_username=student" \
-  -F "new_password=SecurePass123!" \
-  -F "role=user" \
-  -F "daily_limit=50"
+### Using Flutter/Dart:
+
+```dart
+import 'package:http/http.dart' as http;
+
+Future<File> generateTTS(String text) async {
+  final response = await http.post(
+    Uri.parse('https://your-space.hf.space/api/generate'),
+    body: {
+      'text': text,
+      'voice': 'bf_isabella',
+      'speed': '1.0',
+    },
+  );
+  
+  final file = File('${Directory.systemTemp.path}/tts_${DateTime.now().millisecondsSinceEpoch}.wav');
+  await file.writeAsBytes(response.bodyBytes);
+  return file;
+}
 ```
 
-## ⚡ Performance Comparison
+## 📊 API Endpoints
 
-| Model | Speed | Quality | CPU Usage | Max Chars |
-|-------|-------|---------|-----------|-----------|
-| **Kokoro** | **10x** | High | Low | 5000 |
-| XTTS v2 | 1x | Very High | High | 3000 |
-| Bark | 0.5x | High | Very High | 1000 |
+### `POST /api/generate`
 
-## 🎯 Perfect For
+Generate TTS audio from text.
 
-- ✅ Long-form educational content
-- ✅ Audiobook narration
-- ✅ Real-time reader mode in apps
-- ✅ Storytelling with emotion
-- ✅ Multi-voice projects
+**Parameters:**
+- `text` (required): Text to convert (5-4500 characters)
+- `voice` (optional): Voice to use (default: `bf_isabella`)
+- `speed` (optional): Speech speed 0.5-2.0 (default: 1.0)
 
-## 🔧 Integration Example (Flutter)
+**Response:** WAV audio file
 
-Update your `AIService.dart`:
-```dart
-final response = await http.post(
-  Uri.parse('https://your-space.hf.space/api/generate'),
-  headers: {'Content-Type': 'multipart/form-data'},
-  body: {
-    'username': 'your_username',
-    'password': 'your_password',
-    'text': text,
-    'voice': 'bf_isabella',  // Storytelling voice
-    'speed': '1.0'
-  }
-);
-```
+### `GET /health`
 
-## 📊 Quota System
+Check service health and available voices.
 
-| Role | Daily Limit | Speed Limit |
-|------|-------------|-------------|
-| User | 50 generations | Normal |
-| Premium | Custom | Priority |
-| Admin | Unlimited | Highest |
+### `GET /docs`
 
-## 🌐 Deploy to Hugging Face
+Interactive API documentation (Swagger UI).
 
-1. Push to GitHub
-2. Create new Space on Hugging Face
-3. Set secrets: `SUPABASE_URL`, `SUPABASE_KEY`
-4. Deploy!
+## ⚙️ Technical Specs
 
----
+- **Model**: Kokoro-82M (ONNX)
+- **Max Characters**: 4500 (~5 minutes audio)
+- **Generation Time**: ~20-30 seconds (CPU)
+- **Speech Rate**: ~900 characters/minute
+- **Output Format**: WAV, 24kHz
+
+## 🛠️ Deployment
+
+This Space runs on Docker with automatic model download on startup.
+
+**No environment variables needed!**
+
+## 📝 License
+
+Model: Kokoro TTS by thewh1teagle  
+Service: MIT License
+
+## 🔗 Links
 
-**Built for [Studify](https://github.com/your-repo)** - Making education accessible through AI
+- [Kokoro GitHub](https://github.com/thewh1teagle/kokoro-onnx)
+- [API Docs](/docs)
+- [Health Check](/health)

app.py

@@ -3,52 +3,14 @@ from fastapi.responses import FileResponse
 from kokoro_onnx import Kokoro
 import tempfile
 import os
-import bcrypt
-from datetime import datetime, timedelta
-from supabase import create_client, Client
+from datetime import datetime
 import soundfile as sf
 
 # ============== CONFIG ==============
-SUPABASE_URL = os.getenv("SUPABASE_URL")
-SUPABASE_KEY = os.getenv("SUPABASE_KEY")
-
-if not SUPABASE_URL or not SUPABASE_KEY:
-    raise ValueError("SUPABASE_URL and SUPABASE_KEY environment variables must be set")
-
-DAILY_QUOTA = 50  # Increased since Kokoro is much faster
 MAX_CHARS = 4500  # ~5 minutes of audio (speaking rate: ~900 chars/min)
 MIN_CHARS = 5
 MAX_AUDIO_DURATION = 300  # 5 minutes of audio
 
-# Admin credentials
-ADMIN_USERNAME = "madhab"
-ADMIN_PASSWORD = "Madhab@Studify2024!"
-
-# ============== SUPABASE ==============
-supabase: Client = create_client(SUPABASE_URL, SUPABASE_KEY)
-
-def init_admin():
-    """Create admin user if not exists"""
-    try:
-        result = supabase.table("tts_users").select("username").eq("username", ADMIN_USERNAME).execute()
-        
-        if not result.data:
-            password_hash = bcrypt.hashpw(ADMIN_PASSWORD.encode(), bcrypt.gensalt()).decode()
-            supabase.table("tts_users").insert({
-                "username": ADMIN_USERNAME,
-                "password_hash": password_hash,
-                "role": "admin",
-                "daily_limit": -1,
-                "is_active": True
-            }).execute()
-            print(f"✅ Admin user created: {ADMIN_USERNAME}")
-        else:
-            print(f"✅ Admin user exists: {ADMIN_USERNAME}")
-    except Exception as e:
-        # Ignore RLS errors - user may already exist or require manual creation
-        print(f"⚠️  Note: {e}")
-        print(f"ℹ️  Tip: Create admin user manually in Supabase if needed")
-
 # ============== KOKORO TTS MODEL ==============
 print("🎤 Loading Kokoro TTS model...")
 try:
@@ -58,14 +20,17 @@ except Exception as e:
     print(f"⚠️  Kokoro not found locally. Will download on first use.")
     kokoro = None
 
-app = FastAPI(title="Kokoro TTS API - Professional & Fast")
+app = FastAPI(
+    title="Kokoro TTS API - Fast & Simple",
+    description="High-speed text-to-speech with emotional voices",
+    version="2.0"
+)
 
 @app.on_event("startup")
 def startup():
     global kokoro
     if kokoro is None:
         import urllib.request
-        import os
         
         print("📥 Downloading Kokoro TTS model files...")
         
@@ -95,79 +60,32 @@ def startup():
         print("🎤 Initializing Kokoro TTS...")
         kokoro = Kokoro(model_file, voices_file)
         print("✅ Kokoro TTS loaded!")
-    
-    init_admin()
-
-# ============== AUTH ==============
-def verify_password(plain_password: str, hashed_password: str) -> bool:
-    try:
-        return bcrypt.checkpw(plain_password.encode(), hashed_password.encode())
-    except:
-        return False
-
-def authenticate_user(username: str, password: str) -> dict:
-    result = supabase.table("tts_users").select("*").eq("username", username).execute()
-    
-    if not result.data or len(result.data) == 0:
-        raise HTTPException(status_code=401, detail="Access denied. User not found in database.")
-    
-    user = result.data[0]
-    
-    if not user.get('is_active', True):
-        raise HTTPException(status_code=403, detail="Account is disabled. Contact admin.")
-    
-    if not verify_password(password, user['password_hash']):
-        raise HTTPException(status_code=401, detail="Invalid credentials.")
-    
-    return user
-
-def check_quota(username: str, daily_limit: int, role: str) -> dict:
-    if role == 'admin' or daily_limit == -1:
-        return {"used": 0, "remaining": -1, "is_unlimited": True}
-    
-    since = (datetime.utcnow() - timedelta(hours=24)).isoformat()
-    result = supabase.table("tts_usage_logs").select("id", count="exact").eq("username", username).gte("created_at", since).execute()
-    
-    used = result.count or 0
-    remaining = daily_limit - used
-    
-    if remaining <= 0:
-        raise HTTPException(status_code=429, detail=f"Daily quota exceeded. Used {used}/{daily_limit}. Resets in 24h.")
-    
-    return {"used": used, "remaining": remaining, "is_unlimited": False}
-
-def log_usage(username: str, text_length: int, language: str):
-    supabase.table("tts_usage_logs").insert({
-        "username": username,
-        "text_length": text_length,
-        "language": language,
-        "created_at": datetime.utcnow().isoformat()
-    }).execute()
 
 # ============== HELPERS ==============
 def cleanup_file(path: str):
+    """Delete temporary file after response is sent"""
     try:
         if os.path.exists(path):
             os.unlink(path)
     except:
         pass
 
-def generate_speech(text: str, voice: str = "af_heart", speed: float = 1.0) -> str:
+def generate_speech(text: str, voice: str = "bf_isabella", speed: float = 1.0) -> str:
     """
     Generate speech using Kokoro TTS
-    Available voices: af (American Female), am (American Male), bf (British Female), etc.
+    Available voices: af_heart, af_bella, am_adam, am_michael, bf_emma, bf_isabella
     """
     if len(text) < MIN_CHARS:
         raise ValueError(f"Text too short. Minimum {MIN_CHARS} characters.")
     if len(text) > MAX_CHARS:
-        raise ValueError(f"Text too long. Maximum {MAX_CHARS} characters.")
+        raise ValueError(f"Text too long. Maximum {MAX_CHARS} characters (~5 min audio).")
     
     # Generate audio samples
     samples, sample_rate = kokoro.create(
         text=text,
         voice=voice,
         speed=speed,
-        lang="en-us"  # Kokoro supports: en-us, en-gb, ja, etc.
+        lang="en-us"
     )
     
     # Save to temporary file
@@ -176,66 +94,88 @@ def generate_speech(text: str, voice: str = "af_heart", speed: float = 1.0) -> s
         return tmp.name
 
 # ============== API ENDPOINTS ==============
+@app.get("/")
+def root():
+    return {
+        "service": "Kokoro TTS API",
+        "status": "running",
+        "model": "Kokoro-82M",
+        "version": "2.0",
+        "features": {
+            "speed": "10x faster than XTTS",
+            "voices": 6,
+            "max_chars": MAX_CHARS,
+            "emotional": True
+        },
+        "endpoints": {
+            "health": "/health",
+            "generate": "/api/generate (POST)",
+            "docs": "/docs"
+        }
+    }
+
 @app.get("/health")
 def health():
     return {
         "status": "healthy",
         "model": "Kokoro TTS 82M",
         "speed": "10x faster than XTTS",
-        "authentication": "required",
-        "default_quota": DAILY_QUOTA
+        "max_chars": MAX_CHARS,
+        "voices": ["af_heart", "af_bella", "am_adam", "am_michael", "bf_emma", "bf_isabella"]
     }
 
 @app.post("/api/generate")
 async def generate_tts(
     background_tasks: BackgroundTasks,
-    username: str = Form(...),
-    password: str = Form(...),
-    text: str = Form(...),
-    voice: str = Form("af_heart"),  # American Female - Heart
-    speed: float = Form(1.0)
+    text: str = Form(..., description="Text to convert to speech"),
+    voice: str = Form("bf_isabella", description="Voice to use"),
+    speed: float = Form(1.0, description="Speech speed (0.5-2.0)")
 ):
     """
     Generate TTS with Kokoro (Fast & Emotional)
     
-    Performance:
-    - Max audio length: 5 minutes
-    - Speaking rate: ~900 chars/minute
-    - Max chars: 4500 (~5 min audio)
-    - Generation time: ~20-30 seconds on CPU
-    
-    Available voices:
-    - af_heart: American Female (warm)
-    - af_bella: American Female (professional)
-    - am_adam: American Male (confident)
-    - am_michael: American Male (friendly) 
-    - bf_emma: British Female (elegant)
-    - bf_isabella: British Female (storytelling) ⭐
-    
-    Usage:
-    curl -X POST https://your-service.hf.space/api/generate \
-      -F "username=madhab" \
-      -F "password=Madhab@Studify2024!" \
-      -F "text=Hello world. This is much faster!" \
-      -F "voice=bf_isabella" \
-      -F "speed=1.0" \
-      --output output.wav
+    **Performance:**
+    - Max audio: 5 minutes (4500 chars)
+    - Generation: ~20-30 seconds on CPU
+    - Speech rate: ~900 chars/minute
+    
+    **Available Voices:**
+    - `af_heart`: American Female (warm)
+    - `af_bella`: American Female (professional)
+    - `am_adam`: American Male (confident)
+    - `am_michael`: American Male (friendly)
+    - `bf_emma`: British Female (elegant)
+    - `bf_isabella`: British Female (storytelling) ⭐ Best for long content
+    
+    **Example:**
+    ```bash
+    curl -X POST https://your-space.hf.space/api/generate \\
+      -F "text=Hello world, this is Kokoro TTS!" \\
+      -F "voice=bf_isabella" \\
+      -F "speed=1.0" \\
+      --output audio.wav
+    ```
     """
-    user = authenticate_user(username, password)
-    quota = check_quota(user['username'], user['daily_limit'], user['role'])
-    
     try:
-        output_path = generate_speech(text.strip(), voice, speed)
+        # Validate speed
+        if speed < 0.5 or speed > 2.0:
+            raise HTTPException(status_code=400, detail="Speed must be between 0.5 and 2.0")
         
-        if not quota['is_unlimited']:
-            log_usage(user['username'], len(text), "en")
+        # Generate speech
+        output_path = generate_speech(text.strip(), voice, speed)
         
+        # Schedule cleanup after response is sent
         background_tasks.add_task(cleanup_file, output_path)
         
-        response = FileResponse(output_path, media_type="audio/wav", filename="kokoro_tts.wav")
-        response.headers["X-Quota-Used"] = str(quota["used"] + (0 if quota["is_unlimited"] else 1))
-        response.headers["X-Quota-Remaining"] = "unlimited" if quota["is_unlimited"] else str(quota["remaining"] - 1)
-        response.headers["X-Model"] = "Kokoro-82M"
+        # Return audio file
+        response = FileResponse(
+            output_path, 
+            media_type="audio/wav", 
+            filename=f"kokoro_{datetime.now().strftime('%Y%m%d_%H%M%S')}.wav"
+        )
+        response.headers["X-Character-Count"] = str(len(text))
+        response.headers["X-Voice-Used"] = voice
+        
         return response
         
     except ValueError as e:
@@ -243,74 +183,6 @@ async def generate_tts(
     except Exception as e:
         raise HTTPException(status_code=500, detail=f"TTS generation failed: {str(e)}")
 
-@app.post("/api/quota")
-async def check_user_quota(username: str = Form(...), password: str = Form(...)):
-    user = authenticate_user(username, password)
-    quota = check_quota(user['username'], user['daily_limit'], user['role'])
-    
-    return {
-        "username": user['username'],
-        "role": user['role'],
-        "used_today": quota["used"],
-        "remaining": "unlimited" if quota["is_unlimited"] else quota["remaining"],
-        "daily_limit": "unlimited" if quota["is_unlimited"] else user['daily_limit']
-    }
-
-@app.post("/api/admin/create-user")
-async def create_user(
-    admin_username: str = Form(...),
-    admin_password: str = Form(...),
-    new_username: str = Form(...),
-    new_password: str = Form(...),
-    role: str = Form("user"),
-    daily_limit: int = Form(50)
-):
-    admin = authenticate_user(admin_username, admin_password)
-    if admin['role'] != 'admin':
-        raise HTTPException(status_code=403, detail="Admin access required")
-    
-    existing = supabase.table("tts_users").select("username").eq("username", new_username).execute()
-    if existing.data:
-        raise HTTPException(status_code=400, detail="Username already exists")
-    
-    password_hash = bcrypt.hashpw(new_password.encode(), bcrypt.gensalt()).decode()
-    
-    supabase.table("tts_users").insert({
-        "username": new_username,
-        "password_hash": password_hash,
-        "role": role,
-        "daily_limit": daily_limit,
-        "is_active": True
-    }).execute()
-    
-    return {"success": True, "username": new_username, "role": role, "daily_limit": daily_limit}
-
-@app.post("/api/admin/list-users")
-async def list_users(admin_username: str = Form(...), admin_password: str = Form(...)):
-    admin = authenticate_user(admin_username, admin_password)
-    if admin['role'] != 'admin':
-        raise HTTPException(status_code=403, detail="Admin access required")
-    
-    result = supabase.table("tts_users").select("username, role, daily_limit, is_active, created_at").execute()
-    return {"users": result.data}
-
-# ============== ROOT ENDPOINT ==============
-@app.get("/")
-def root():
-    return {
-        "service": "Kokoro TTS API",
-        "status": "running",
-        "model": "Kokoro-82M",
-        "version": "1.0",
-        "endpoints": {
-            "health": "/health",
-            "generate": "/api/generate (POST)",
-            "quota": "/api/quota (POST)",
-            "docs": "/docs"
-        },
-        "usage": "Visit /docs for interactive API documentation"
-    }
-
 if __name__ == "__main__":
     import uvicorn
     uvicorn.run(app, host="0.0.0.0", port=7860)

requirements.txt

@@ -3,7 +3,4 @@ uvicorn[standard]==0.32.0
 kokoro-onnx
 soundfile
 python-multipart
-bcrypt==4.1.2
-supabase==2.0.2
 numpy
-huggingface-hub==0.20.3