An institutional-grade web interface for high-fidelity speech synthesis, powered by the Murf AI SDK and FastAPI.
- Crystal Clear Audio: Leverages Murf's studio-quality AI voices.
- Modern UI: A sleek, reactive dashboard built with pure CSS glassmorphism and smooth animations.
- Real-time Customization: Adjust speed (
rate) and tone (pitch) to fine-tune the output. - Pause Control: Easily insert standard, strong, or extra-strong pauses directly into your text.
- Voice Discovery: Automatically fetches and filters the best available English voices from the Murf library.
- Audio Visualizer: Interactive visual feedback during playback.
- Download Ready: Generate and save your synthesized speech as MP3 files instantly.
- Backend: Python 3.x, FastAPI, Murf SDK, Uvicorn
- Frontend: Vanilla HTML5, CSS3 (Glassmorphism), JavaScript (ES6+)
- Integration: Murf API (Text-to-Speech)
- Styling: Google Fonts (Outfit), CSS Variable Tokens
- Python 3.8+
- Murf API Key
-
Clone the repository
git clone <repository-url> cd "text to speech"
-
Install dependencies
pip install -r requirements.txt
-
Set up environment variables Create a
.envfile in the root directory:MURF_API_KEY=your_api_key_here
-
Run the application
python -m app.main
The app will be available at
http://localhost:8000.
app/
├── main.py # FastAPI backend & Murf integration
├── static/
│ ├── script.js # Frontend logic & Audio handling
│ └── style.css # Premium glassmorphic styles
└── templates/
└── index.html # Core application interface
tests/ # SDK validation & connectivity scripts
requirements.txt # Python dependencies
- Murf SDK Integration: Fully migrated to the official Murf Python SDK.
- Dynamic Voice Loading: Voices are now fetched live from the API with gender and locale metadata.
- Murf SDK Integration: Fully migrated to the official Murf Python SDK.
- Dynamic Voice Loading: Voices are now fetched live from the API with gender and locale metadata.
- Security First: Using
.envand.gitignoreto keep credentials safe.