# SimpleTTS
A lightweight Python library for text-to-speech synthesis that makes it easy to use and switch between different TTS models.
> [!NOTE]
> This project is under active development and APIs may change. Not recommended for production use yet.
## Features
- 🚀 Simple and intuitive API - get started in minutes
- 🔄 No model lock-in - switch models with just a few lines of code
- 🎯 Focus on ease of use - a single API for all models
- 📦 Minimal dependencies - one package for all models
- 🔌 Extensible architecture - easily add new models
## Installation
Install the latest release from PyPI:
```bash
pip install simpletts
```
Or get the latest version from source:
```bash
pip install git+https://github.com/fakerybakery/simpletts
```
## Quick Start
```python
from simpletts.models.xtts import XTTS
import soundfile as sf
tts = XTTS(device="auto")
# Note: XTTS is licensed under the CPML license which restricts commercial use.
array, sr = tts.synthesize("Hello, world!", ref="sample.wav")
sf.write("output.wav", array, sr)
```
## Supported Models
| Model | License | Description |
|-------|---------|-------------|
| XTTS | CPML | High-quality multilingual TTS with voice cloning capabilities |
| Kokoro | Apache-2.0 | Fast and lightweight English TTS with voice cloning |
| F5-TTS | CC BY-NC | Superb voice cloning and naturalness, but slower and less stable |
| Parler TTS | Apache-2.0 | Describe a voice with a text prompt |
> [!NOTE]
> If you are trying to install Parler TTS, you may run into dependency conflicts or other issues. Parler TTS is not officially supported by the SimpleTTS project, please do not report issues to the SimpleTTS project if you run into issues.
>
> Parler TTS is not officially available on PyPI, so we cannot add it as a required dependency due to PyPI security requirements. We have published several unofficial packages for Parler TTS and its dependencies to PyPI, however this is not guaranteed to work.
>
> If you run into issues, please try running `pip uninstall parler-tts` and then `pip install git+https://github.com/huggingface/parler-tts`.
## Roadmap
**Models**
- [x] XTTS - Production-ready multilingual TTS
- [x] Kokoro - StyleTTS 2-based English TTS without voice cloning
- [x] F5-TTS - Superb voice cloning and naturalness, but slower and less stable
- [x] Parler TTS - Describe a voice with a text prompt
- [ ] StyleTTS 2 - Fast and efficient zero-shot voice cloning
- [ ] CosyVoice2 - Zero-shot voice cloning
- [ ] MetaVoice - 1.1B parameter zero-shot voice cloning model
- [ ] Fish Speech 1.5 - Zero-shot voice cloning
- [ ] OpenVoice V2 - Open source zero-shot voice cloning by MyShell
**Features**
- [x] Simple Python API for easy integration
- [ ] Command-line interface for quick testing and batch processing
- [ ] REST API and web interface for remote access
- [ ] Model benchmarking tools
- [ ] Batch processing support
- [ ] Audio post-processing options
- [ ] Allow easier extensibility with a plugin system
## Support & Feedback
If you encounter any issues or have questions, please open an [issue](https://github.com/fakerybakery/simpletts/issues).
## License
This project is licensed under the **BSD-3-Clause** license. See the [LICENSE](LICENSE) file for more details.
While SimpleTTS itself is open source and can be used commercially, please note that some supported models have different licensing terms:
- XTTS is licensed under CPML which restricts commercial use
- Kokoro is licensed under Apache-2.0 which allows commercial use
- Other models may have their own licensing requirements
Note that SimpleTTS **does not** use the GPL-licensed `phonemizer` library. Instead, it uses the BSD-licensed `openphonemizer` alternative. While this may slightly reduce pronunciation accuracy, it's license is compatible with the BSD-3-Clause license of SimpleTTS.
For complete licensing information for all included models and dependencies, please see the `licenses` directory.
Raw data
{
"_id": null,
"home_page": "https://github.com/fakerybakery/simpletts",
"name": "simpletts",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": null,
"author": "mrfakename",
"author_email": "me@mrfake.name",
"download_url": "https://files.pythonhosted.org/packages/97/d3/256e7ddf2bb861879f2c0b70c560c06fa9cbdcd2c56b20e3ff64523b5dab/simpletts-0.0.2.tar.gz",
"platform": null,
"description": "# SimpleTTS\n\nA lightweight Python library for text-to-speech synthesis that makes it easy to use and switch between different TTS models.\n\n> [!NOTE]\n> This project is under active development and APIs may change. Not recommended for production use yet.\n\n## Features\n\n- \ud83d\ude80 Simple and intuitive API - get started in minutes\n- \ud83d\udd04 No model lock-in - switch models with just a few lines of code\n- \ud83c\udfaf Focus on ease of use - a single API for all models\n- \ud83d\udce6 Minimal dependencies - one package for all models\n- \ud83d\udd0c Extensible architecture - easily add new models\n\n## Installation\n\nInstall the latest release from PyPI:\n\n```bash\npip install simpletts\n```\n\nOr get the latest version from source:\n\n```bash\npip install git+https://github.com/fakerybakery/simpletts\n```\n\n## Quick Start\n\n```python\nfrom simpletts.models.xtts import XTTS\nimport soundfile as sf\n\ntts = XTTS(device=\"auto\")\n# Note: XTTS is licensed under the CPML license which restricts commercial use.\n\narray, sr = tts.synthesize(\"Hello, world!\", ref=\"sample.wav\")\n\nsf.write(\"output.wav\", array, sr)\n```\n\n## Supported Models\n\n| Model | License | Description |\n|-------|---------|-------------|\n| XTTS | CPML | High-quality multilingual TTS with voice cloning capabilities |\n| Kokoro | Apache-2.0 | Fast and lightweight English TTS with voice cloning |\n| F5-TTS | CC BY-NC | Superb voice cloning and naturalness, but slower and less stable |\n| Parler TTS | Apache-2.0 | Describe a voice with a text prompt |\n\n> [!NOTE]\n> If you are trying to install Parler TTS, you may run into dependency conflicts or other issues. Parler TTS is not officially supported by the SimpleTTS project, please do not report issues to the SimpleTTS project if you run into issues.\n> \n> Parler TTS is not officially available on PyPI, so we cannot add it as a required dependency due to PyPI security requirements. We have published several unofficial packages for Parler TTS and its dependencies to PyPI, however this is not guaranteed to work.\n>\n> If you run into issues, please try running `pip uninstall parler-tts` and then `pip install git+https://github.com/huggingface/parler-tts`.\n\n## Roadmap\n\n**Models**\n\n- [x] XTTS - Production-ready multilingual TTS\n- [x] Kokoro - StyleTTS 2-based English TTS without voice cloning\n- [x] F5-TTS - Superb voice cloning and naturalness, but slower and less stable\n- [x] Parler TTS - Describe a voice with a text prompt\n- [ ] StyleTTS 2 - Fast and efficient zero-shot voice cloning\n- [ ] CosyVoice2 - Zero-shot voice cloning\n- [ ] MetaVoice - 1.1B parameter zero-shot voice cloning model\n- [ ] Fish Speech 1.5 - Zero-shot voice cloning\n- [ ] OpenVoice V2 - Open source zero-shot voice cloning by MyShell\n\n**Features**\n\n- [x] Simple Python API for easy integration\n- [ ] Command-line interface for quick testing and batch processing\n- [ ] REST API and web interface for remote access\n- [ ] Model benchmarking tools\n- [ ] Batch processing support\n- [ ] Audio post-processing options\n- [ ] Allow easier extensibility with a plugin system\n\n## Support & Feedback\n\nIf you encounter any issues or have questions, please open an [issue](https://github.com/fakerybakery/simpletts/issues).\n\n## License\n\nThis project is licensed under the **BSD-3-Clause** license. See the [LICENSE](LICENSE) file for more details.\n\nWhile SimpleTTS itself is open source and can be used commercially, please note that some supported models have different licensing terms:\n\n- XTTS is licensed under CPML which restricts commercial use\n- Kokoro is licensed under Apache-2.0 which allows commercial use\n- Other models may have their own licensing requirements\n\nNote that SimpleTTS **does not** use the GPL-licensed `phonemizer` library. Instead, it uses the BSD-licensed `openphonemizer` alternative. While this may slightly reduce pronunciation accuracy, it's license is compatible with the BSD-3-Clause license of SimpleTTS.\n\nFor complete licensing information for all included models and dependencies, please see the `licenses` directory.\n",
"bugtrack_url": null,
"license": "BSD-3-Clause",
"summary": "Easily run and use TTS models with just a few lines of code.",
"version": "0.0.2",
"project_urls": {
"Bug Tracker": "https://github.com/fakerybakery/simpletts/issues",
"Documentation": "https://github.com/fakerybakery/simpletts/wiki",
"Homepage": "https://github.com/fakerybakery/simpletts",
"Source Code": "https://github.com/fakerybakery/simpletts"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "97d3256e7ddf2bb861879f2c0b70c560c06fa9cbdcd2c56b20e3ff64523b5dab",
"md5": "24cce6e724dcd93d7d081d4e9242c7e8",
"sha256": "f317f94d24b5ce3fd4988e6b5557e09bcbe2fdb02db78fcfdfe3b0a78e9bfb90"
},
"downloads": -1,
"filename": "simpletts-0.0.2.tar.gz",
"has_sig": false,
"md5_digest": "24cce6e724dcd93d7d081d4e9242c7e8",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 19517,
"upload_time": "2025-01-09T23:04:04",
"upload_time_iso_8601": "2025-01-09T23:04:04.809794Z",
"url": "https://files.pythonhosted.org/packages/97/d3/256e7ddf2bb861879f2c0b70c560c06fa9cbdcd2c56b20e3ff64523b5dab/simpletts-0.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-01-09 23:04:04",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "fakerybakery",
"github_project": "simpletts",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "simpletts"
}
JSON
