Upload README.md

README.md

@@ -1,5 +1,5 @@
 ---
-title: Test Space of SpeechBrain TTS API
+title: SpeechBrain TTS API Test 
 emoji: 🗣️
 colorFrom: blue
 colorTo: purple
@@ -10,137 +10,4 @@ pinned: false
 license: mit
 ---
 
-# Test Space of SpeechBrain TTS API 
-
-This is test of A Text-to-Speech API built with FastAPI and SpeechBrain, running on Hugging Face Spaces.
-
-## Features
-
-- 🎯 **Fast TTS synthesis** using SpeechBrain's Tacotron2 + HiFiGAN
-- 🔄 **Multiple output formats** (WAV stream and Base64)
-- 📝 **Simple REST API** with JSON requests
-- 🚀 **Ready for deployment** on Hugging Face Spaces
-
-## API Endpoints
-
-### `GET /`
-Returns API status message.
-
-### `GET /health`
-Health check endpoint.
-
-### `POST /synthesize`
-Synthesizes speech and returns audio as WAV stream.
-
-**Request:**
-```json
-{
-  "text": "Hello, this is a test message",
-  "sample_rate": 22050
-}
-```
-
-**Response:** WAV audio file stream
-
-### `POST /synthesize_base64`
-Synthesizes speech and returns audio as Base64 encoded string.
-
-**Request:**
-```json
-{
-  "text": "Hello, this is a test message", 
-  "sample_rate": 22050
-}
-```
-
-**Response:**
-```json
-{
-  "audio_base64": "UklGRkq...",
-  "sample_rate": 22050,
-  "text": "Hello, this is a test message"
-}
-```
-
-## Usage Examples
-
-### Python Client
-```python
-import requests
-import base64
-from io import BytesIO
-
-# Text to synthesize
-text = "Hello world, this is a speech synthesis test."
-
-# Request to Base64 endpoint
-response = requests.post(
-    "https://your-space-url.hf.space/synthesize_base64",
-    json={"text": text, "sample_rate": 22050}
-)
-
-if response.status_code == 200:
-    result = response.json()
-    
-    # Decode Base64 audio
-    audio_data = base64.b64decode(result["audio_base64"])
-    
-    # Save as WAV file
-    with open("output.wav", "wb") as f:
-        f.write(audio_data)
-    
-    print("Audio saved as output.wav")
-```
-
-### JavaScript Client
-```javascript
-async function synthesizeSpeech(text) {
-    const response = await fetch('/synthesize_base64', {
-        method: 'POST',
-        headers: {
-            'Content-Type': 'application/json',
-        },
-        body: JSON.stringify({
-            text: text,
-            sample_rate: 22050
-        })
-    });
-    
-    if (response.ok) {
-        const result = await response.json();
-        
-        // Create audio element
-        const audio = new Audio();
-        audio.src = `data:audio/wav;base64,${result.audio_base64}`;
-        audio.play();
-    }
-}
-
-// Usage
-synthesizeSpeech("Hello from JavaScript!");
-```
-
-## Local Development
-
-1. Install dependencies:
-```bash
-pip install -r requirements.txt
-```
-
-2. Run the server:
-```bash
-python app.py
-```
-
-3. The API will be available at `http://localhost:7860`
-
-## Model Information
-
-- **TTS Model:** SpeechBrain Tacotron2 (LJSpeech)
-- **Vocoder:** SpeechBrain HiFiGAN (LJSpeech)
-- **Default Sample Rate:** 22,050 Hz
-- **Text Limit:** 500 characters per request
-
-## License
-
-MIT License
+This is a test of A Text-to-Speech API built with FastAPI and SpeechBrain.