- Home
- Text-to-speech tools
- GPT-SoVITS
GPT-SoVITS
What it is
GPT-SoVITS is a free WebUI for voice conversion and text-to-speech. It can generate speech using a five-second vocal sample, or use a minute of training data to fine-tune a model for greater voice similarity and realism. Cross-lingual inference supports English, Japanese, Korean, Cantonese, and Chinese. The WebUI provides tools for separating accompaniment, preparing training sets through automatic segmentation, multilingual speech recognition, and text labeling. Recognition options include Fun-ASR-Nano, SenseVoice, classic FunASR, and Faster Whisper. The repository also includes an API with GET and POST inference endpoints that return WAV audio streams on success. Installation instructions cover Windows, Linux, and macOS, and Docker Compose services are documented in full and Lite variants. The Lite image lacks ASR and UVR5 models; UVR5 models need manual downloading, while ASR models download as needed. On macOS, the project temporarily uses CPUs because it reports lower quality from models trained with Mac GPUs. The software uses the MIT License and links to Chinese and English user guides.
For and against
For
- Speech generation can start from a five-second sample
- Supports cross-lingual inference in five languages
- Includes dataset preparation and labeling tools
- Offers API inference endpoints
- Released under the MIT License
Against
- Lite Docker image omits ASR and UVR5 models
- UVR5 models require manual download in Lite
- macOS uses CPUs temporarily
- GitHub reports no security policy or published advisories
The verdict
GPT-SoVITS offers voice generation, conversion, and dataset tools across several deployment options. The Lite image and macOS setup have stated limitations, and the project has no published security policy.
Who it suits
It suits people seeking a free, self-hostable tool for voice conversion or speech generation, including beginners preparing training datasets. Users can choose among desktop operating systems or documented Docker deployments.
On the record
- API
- The repository includes an API exposing GET and POST inference endpoints that return WAV audio streams on success.github.com · read 1 Oct 2026
- API access
- Yesgithub.com · read 20 Sep 2026
- ASR integrations
- The WebUI lists Fun-ASR-Nano, SenseVoice, and classic FunASR; Faster Whisper is also available as an ASR backend.github.com · read 2 Oct 2026
- Commercial use
- Yesgithub.com · read 20 Sep 2026
- Dataset tools
- WebUI tools include accompaniment separation, automatic training-set segmentation, multilingual ASR, and text labeling.github.com · read 2 Oct 2026
- Deployment
- The project documents Docker images and Docker Compose services, including full and Lite variants.github.com · read 2 Oct 2026
- Docker
- Docker Compose defines full and Lite services for CUDA 12.6 and CUDA 12.8 environments.github.com · read 1 Oct 2026
- Export formats
- wav,ogg,aacgithub.com · read 20 Sep 2026
- Few-shot TTS
- The project says users can fine-tune with one minute of training data to improve voice similarity and realism.github.com · read 2 Oct 2026
- Intended users
- The integrated WebUI tools are described as assisting beginners in creating training datasets and GPT/SoVITS models.github.com · read 1 Oct 2026
- Languages
- Cross-lingual inference supports English, Japanese, Korean, Cantonese, and Chinese.github.com · read 2 Oct 2026
- License
- The repository identifies its license as MIT.github.com · read 2 Oct 2026
- Lite limit
- The Lite Docker image does not include ASR or UVR5 models; UVR5 models must be downloaded manually and ASR models download as needed.github.com · read 2 Oct 2026
- Local API
- The repository includes api.py and api_v2.py alongside the WebUI.github.com · read 2 Oct 2026
- macOS limit
- The README says models trained with Mac GPUs produce significantly lower quality than models trained on other devices, so it temporarily uses CPUs instead.github.com · read 2 Oct 2026
- macOS limitation
- The project says models trained with GPUs on Macs have significantly lower quality and therefore temporarily uses CPUs on macOS.github.com · read 1 Oct 2026
- Operating systems
- Installation instructions are provided for Windows, Linux, and macOS.github.com · read 2 Oct 2026
- Product
- GPT-SoVITS is a WebUI for few-shot voice conversion and text-to-speech.github.com · read 2 Oct 2026
