{"name":"GPT-SoVITS: Few-Shot Voice Cloning and Text-to-Speech WebUI","description":"GPT-SoVITS is a powerful web-based tool for few-shot voice conversion and text-to-speech. It allows users to train a high-quality TTS model with as little as one minute of voice data. This project offers robust voice cloning capabilities and cross-lingual support, making advanced voice synthesis accessible.","github":"https://github.com/RVC-Boss/GPT-SoVITS","url":"https://osrepos.com/repo/rvc-boss-gpt-sovits","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/rvc-boss-gpt-sovits","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/rvc-boss-gpt-sovits.md","json":"https://osrepos.com/repo/rvc-boss-gpt-sovits.json","topics":["text-to-speech","tts","voice-cloning","voice-conversion","python","ai","machine-learning","open-source"],"keywords":["text-to-speech","tts","voice-cloning","voice-conversion","python","ai","machine-learning","open-source"],"stars":null,"summary":"GPT-SoVITS is a powerful web-based tool for few-shot voice conversion and text-to-speech. It allows users to train a high-quality TTS model with as little as one minute of voice data. This project offers robust voice cloning capabilities and cross-lingual support, making advanced voice synthesis accessible.","content":"## Introduction\n\nGPT-SoVITS-WebUI is a powerful, open-source project designed for few-shot voice conversion and text-to-speech (TTS). It stands out by enabling the training of high-quality TTS models with remarkably little data, often as little as one minute of vocal input. The project provides a user-friendly web interface, making advanced voice synthesis technologies accessible to a wider audience.\n\nKey features include:\n* **Zero-shot TTS:** Instant text-to-speech conversion using just a 5-second vocal sample.\n* **Few-shot TTS:** Fine-tune the model with only 1 minute of training data for enhanced voice similarity and realism.\n* **Cross-lingual Support:** Perform inference in languages different from the training dataset, currently supporting English, Japanese, Korean, Cantonese, and Chinese.\n* **Integrated WebUI Tools:** Tools for voice accompaniment separation, automatic training set segmentation, ASR (Automatic Speech Recognition), and text labeling are included to assist in creating training datasets and GPT/SoVITS models.\n\n## Installation\n\nGPT-SoVITS supports various environments including Windows, Linux, macOS, and Docker.\n\n### Prerequisites\n\nEnsure you have Python 3.10-3.12 and a compatible PyTorch version installed. Conda is recommended for environment management.\n\n### Windows\n\nFor Windows users, an integrated package is available for direct download and execution. Alternatively, you can install via `conda` and `pwsh` script:\n\npwsh\nconda create -n GPTSoVits python=3.10\nconda activate GPTSoVits\npwsh -F install.ps1 --Device --Source [--DownloadUVR5]\n\n\n### Linux\n\nInstall on Linux using `conda` and the `bash` script:\n\nbash\nconda create -n GPTSoVits python=3.10\nconda activate GPTSoVits\nbash install.sh --device --source [--download-uvr5]\n\n\n### macOS\n\nFor macOS, installation also uses `conda` and a `bash` script. Note that GPU training on Macs may yield lower quality, so CPU is often used.\n\nbash\nconda create -n GPTSoVits python=3.10\nconda activate GPTSoVits\nbash install.sh --device --source [--download-uvr5]\n\n\n### Docker\n\nGPT-SoVITS can be run using Docker. Refer to the official repository for detailed Docker image selection, environment variables, and shared memory configuration.\n\nbash\ndocker compose run --service-ports \n\n\n### Pretrained Models\n\nAfter installation, download necessary pretrained models for GPT-SoVITS, G2PW, UVR5, and ASR from the links provided in the official documentation and place them in their respective directories.\n\n## Examples\n\nExperience GPT-SoVITS in action through various demonstrations:\n\n* **Demo Video:** Watch a comprehensive demonstration of its capabilities on [Bilibili](https://www.bilibili.com/video/BV12g4y1m7Uw){:target=\"_blank\"}.\n* **Online Demo:** Try the free online demo hosted on [Hugging Face](https://lj1995-gpt-sovits-proplus.hf.space/){:target=\"_blank\"} for a hands-on experience of high-speed inference.\n* **Few-shot Fine-tuning Demo:** See unseen speakers few-shot fine-tuning in action directly on the [GitHub repository](https://github.com/RVC-Boss/GPT-SoVITS/assets/129054828/05bee1fa-bdd8-4d85-9350-08c060ab47fb){:target=\"_blank\"}.\n\nTo open the WebUI for finetuning or inference, use the provided scripts:\n\nbash\npython webui.py \n\n\nOr for inference:\n\nbash\npython GPT_SoVITS/inference_webui.py \n\n\n## Why Use GPT-SoVITS?\n\nGPT-SoVITS offers several compelling reasons for anyone interested in voice synthesis:\n\n* **Efficiency:** Achieve high-quality voice cloning and TTS with minimal data, significantly reducing the effort and resources typically required.\n* **Versatility:** Its cross-lingual capabilities and support for multiple languages make it suitable for a wide range of global applications.\n* **Comprehensive Toolset:** The integrated WebUI tools simplify the entire process, from dataset preparation to model training and inference, making it beginner-friendly.\n* **High Performance:** The project boasts impressive inference speeds, especially on modern GPUs, ensuring quick and responsive voice generation.\n* **Continuous Improvement:** With ongoing development and multiple versions (V2, V3, V4, V2Pro) introducing new features and enhancements, GPT-SoVITS remains at the forefront of voice synthesis technology.\n\n## Links\n\n* **GitHub Repository:** [https://github.com/RVC-Boss/GPT-SoVITS](https://github.com/RVC-Boss/GPT-SoVITS){:target=\"_blank\"}\n* **English Documentation:** [https://rentry.co/GPT-SoVITS-guide#/](https://rentry.co/GPT-SoVITS-guide#/){:target=\"_blank\"}\n* **Hugging Face Online Demo:** [https://lj1995-gpt-sovits-proplus.hf.space/](https://lj1995-gpt-sovits-proplus.hf.space/){:target=\"_blank\"}\n* **Colab Training:** [https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/Colab-WebUI.ipynb](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/Colab-WebUI.ipynb){:target=\"_blank\"}\n* **Demo Video (Bilibili):** [https://www.bilibili.com/video/BV12g4y1m7Uw](https://www.bilibili.com/video/BV12g4y1m7Uw){:target=\"_blank\"}","metrics":{"detailViews":17,"githubClicks":9},"dates":{"published":null,"modified":"2025-11-25T12:01:04.000Z"}}