Skip to content
SPECIFICTION
Get listed

GPT-SoVITS

github.com

WebWindowsmacOSLinuxAPISelf-hosted
Visit github.com
Spec score 8.1 #87 of 233 in Text-to-speech tools

What it is

GPT-SoVITS is a free WebUI for few-shot voice conversion and text-to-speech. It can generate speech from a five-second vocal sample, or use one minute of training data to improve voice similarity and realism. Cross-lingual inference supports English, Japanese, Korean, Cantonese, and Chinese. The WebUI includes tools for separating accompaniment, segmenting training sets, multilingual speech recognition, and labeling text. Speech-recognition options include Fun-ASR-Nano, SenseVoice, classic FunASR, and Faster Whisper. The repository also provides an API with GET and POST inference endpoints that return WAV audio streams on success. Installation instructions cover Windows, Linux, and macOS, with Docker Compose services in full and Lite variants. The Lite image omits ASR and UVR5 models; UVR5 models must be downloaded manually, while ASR models download as needed. On macOS, the project temporarily uses CPUs because it reports significantly lower quality from models trained with Mac GPUs. GPT-SoVITS is released under the MIT License and links to Chinese and English user guides.

Spec sheet

What it does
GPT-SoVITS is a few-shot voice conversion and text-to-speech WebUI.Read 1 Oct 2026 · github.com
Product
GPT-SoVITS is a WebUI for few-shot voice conversion and text-to-speech.Read 2 Oct 2026 · github.com
Intended users
The integrated WebUI tools are described as assisting beginners in creating training datasets and GPT/SoVITS models.Read 1 Oct 2026 · github.com
Platforms
web,windows,macos,linux,apiRead 20 Sep 2026 · github.com
Deployment
The project documents Docker images and Docker Compose services, including full and Lite variants.Read 2 Oct 2026 · github.com
Free plan
YesRead 20 Sep 2026 · github.com
API
The repository includes an API exposing GET and POST inference endpoints that return WAV audio streams on success.Read 1 Oct 2026 · github.com
License
The repository identifies its license as MIT.Read 2 Oct 2026 · github.com
API access
YesRead 20 Sep 2026 · github.com
ASR integrations
The WebUI lists Fun-ASR-Nano, SenseVoice, and classic FunASR; Faster Whisper is also available as an ASR backend.Read 2 Oct 2026 · github.com
Commercial use
YesRead 20 Sep 2026 · github.com
Dataset tools
WebUI tools include accompaniment separation, automatic training-set segmentation, multilingual ASR, and text labeling.Read 2 Oct 2026 · github.com
Docker
Docker Compose defines full and Lite services for CUDA 12.6 and CUDA 12.8 environments.Read 1 Oct 2026 · github.com
Export formats
wav,ogg,aacRead 20 Sep 2026 · github.com
Few-shot TTS
The project says users can fine-tune with one minute of training data to improve voice similarity and realism.Read 2 Oct 2026 · github.com
Languages
Cross-lingual inference supports English, Japanese, Korean, Cantonese, and Chinese.Read 2 Oct 2026 · github.com
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.Read 2 Oct 2026 · github.com
Local API
The repository includes api.py and api_v2.py alongside the WebUI.Read 2 Oct 2026 · github.com
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.Read 2 Oct 2026 · github.com
macOS limitation
The project says models trained with GPUs on Macs have significantly lower quality and therefore temporarily uses CPUs on macOS.Read 1 Oct 2026 · github.com
Operating systems
Installation instructions are provided for Windows, Linux, and macOS.Read 2 Oct 2026 · github.com
Security policy
GitHub reports that the project has no SECURITY.md security policy and no published security advisories.Read 1 Oct 2026 · github.com
Support material
The README links to Chinese and English user guides.Read 1 Oct 2026 · github.com
User guide
The README links to Chinese and English user guides.Read 2 Oct 2026 · github.com
Voice cloning
YesRead 20 Sep 2026 · github.com
WebUI tools
The WebUI includes voice accompaniment separation, automatic training-set segmentation, multilingual ASR, and text labeling.Read 1 Oct 2026 · github.com
Windows support
Windows users tested on Windows 10 or newer can download an integrated package and start the WebUI with go-webui.bat.Read 1 Oct 2026 · github.com
Zero-shot TTS
Zero-shot text-to-speech can use a 5-second vocal sample.Read 2 Oct 2026 · github.com

Strong points and limits

Strong points

  • Free to use under the MIT License.
  • Can generate speech from a five-second sample.
  • Supports five listed languages for cross-lingual inference.
  • WebUI includes dataset preparation tools.
  • Provides GET and POST inference endpoints.

Limits

  • Lite Docker image omits ASR and UVR5 models.
  • UVR5 models require manual downloading for Lite.
  • macOS temporarily uses CPUs.
  • Project reports lower quality from Mac-GPU-trained models.

Who it suits

GPT-SoVITS suits users creating voice conversion or speech-generation workflows, including beginners using its dataset tools. It also offers an API for inference and supports commercial use under its listed license.

Verdict

GPT-SoVITS combines voice generation, conversion, dataset tools, and API inference in a free WebUI. Note the Lite image omissions and the project’s stated macOS limitation before selecting a deployment path.

Where Specifiction places it

Alternatives to GPT-SoVITSAll alternatives →