GPT-SoVITS

GPT-SoVITS is a speech (TTS/STT) tool - 1 min voice data can also be used to train a good TTS model! (few shot voice cloning).

Overview

GPT-SoVITS-WebUI A Powerful Few-shot Voice Conversion and Text-to-Speech WebUI.

1. Zero-shot TTS: Input a 5-second vocal sample and experience instant text-to-speech conversion.

2. Few-shot TTS: Fine-tune the model with just 1 minute of training data for improved voice similarity and realism.

3. Cross-lingual Support: Inference in languages different from the training dataset, currently supporting English, Japanese, Korean, Cantonese and Chinese.

4. WebUI Tools: Integrated tools include voice accompaniment separation, automatic training set segmentation, multilingual ASR with Fun-ASR-Nano, SenseVoice, and classic FunASR, plus text labeling, assisting beginners in creating training datasets and GPT/SoVITS models.

RTF(inference speed) of GPT-SoVITS v2 ProPlus: 0.028 tested in 4060Ti, 0.014 tested in 4090 (1400words~=4min, inference time is 3.36s), 0.526 in M4 CPU. You can test our huggingface demo (half H200) to experience high-speed inference .

CPU-Optimized Inference Version：https://github.com/baicai-1145/GPT-SoVITS-CPUFast

For users in China, you can click here to use AutoDL Cloud Docker to experience the full functionality online.

If you are a Windows user (tested with win>=10), you can download the integrated package and double-click on go-webui.bat to start GPT-SoVITS-WebUI.

Note: The models trained with GPUs on Macs result in significantly lower quality compared to those trained on other devices, so we are temporarily using CPUs instead.

Download and place ffmpeg.exe and ffprobe.exe in the GPT-SoVITS root

GPT-SoVITS is open-source, written primarily in Python, with 62,277 GitHub stars under the MIT license. The latest release is 20250606v2pro (2025-06-06).

Key capabilities

From the project's documentation:

• Check Docker Hub for the latest available image tags
• Choose an appropriate image tag for your environment
• The appropriate architecture image (amd64/arm64) will be automatically pulled during Docker Compose
• Optionally, build the image locally using the provided Dockerfile for the most up-to-date changes
• GPT-SoVITS-CU126 & GPT-SoVITS-CU128: Full version with all features.
• GPT-SoVITS-CU126-Lite & GPT-SoVITS-CU128-Lite: Lightweight version with reduced dependencies and functionality.

How it fits a local-AI stack

GPT-SoVITS runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related speech (TTS/STT) tools in the directory:

• "cactus"
• "claude-code-local"
• "dograh"
• "DreamServer"

Sources

• Source code & docs: RVC-Boss/GPT-SoVITS

Stats from GitHub, 2026-10-01.