| --- |
| title: Hfstudio |
| emoji: π |
| colorFrom: green |
| colorTo: purple |
| sdk: gradio |
| sdk_version: 5.49.1 |
| app_file: app.py |
| pinned: false |
| --- |
| |
| # HFStudio ποΈ |
|
|
| A local and API-based Text-to-Speech studio for creating high-quality speech from text. |
|
|
| ## Features |
|
|
| - π― **Multiple TTS Models**: Support for various TTS engines |
| - π **Voice Selection**: Choose from different voice models |
| - β‘ **Real-time Generation**: Fast speech synthesis |
| - π§ **Parameter Control**: Fine-tune speed, stability, and similarity |
| - π΅ **Audio Preview**: Built-in audio player with controls |
| - π **HuggingFace Integration**: Automatic sign-in with your HF account (OAuth enabled) |
|
|
| ## Quick Start |
|
|
| This Space runs HFStudio automatically. Simply: |
|
|
| 1. **Open the Space** - The web interface will load automatically |
| 2. **Sign In** (automatic) - You'll be automatically signed in with your HuggingFace account |
| 3. **Enter Text** - Type or paste the text you want to convert to speech |
| 4. **Choose Voice** - Select from available voice models |
| 5. **Adjust Settings** - Tune speed, stability, and other parameters |
| 6. **Generate** - Click "Generate speech" to create audio |
| 7. **Play & Download** - Use the built-in player to preview your audio |
|
|
| ## Local Installation |
|
|
| Want to run HFStudio locally? Install via pip: |
|
|
| ```bash |
| pip install hfstudio |
| hfstudio |
| ``` |
|
|
| Then visit `http://localhost:7860` in your browser. |
|
|
| ## Development |
|
|
| This Space is automatically synced from the [GitHub repository](https://github.com/yourusername/hfstudio). |
|
|
| To contribute or run locally for development: |
|
|
| ```bash |
| git clone https://github.com/yourusername/hfstudio |
| cd hfstudio |
| ./run_dev.sh # Starts both frontend and backend |
| ``` |
|
|
| ## API Usage |
|
|
| HFStudio also provides a REST API for integration: |
|
|
| ```python |
| import requests |
| |
| # Generate speech |
| response = requests.post('https://abidlabs-hfstudio.hf.space/api/tts/generate', |
| json={ |
| "text": "Hello, world!", |
| "voice_id": "sarah", |
| "model_id": "coqui-tts" |
| } |
| ) |
| |
| audio_data = response.json() |
| print(f"Audio URL: {audio_data['audio_url']}") |
| ``` |
|
|
| ## License |
|
|
| MIT License - see [LICENSE](LICENSE) for details. |
|
|
| --- |
|
|
| Built with β€οΈ using [SvelteKit](https://kit.svelte.dev/) and [FastAPI](https://fastapi.tiangolo.com/) |