GPT-Sovits4

字数

405 字

阅读

3 分钟

GPT-Sovits4 是一个领先的多语言语音生成工具，支持普通话、英语、日语等多种语言和方言，提供高音质、即时响应、丰富表现力和简单部署的功能。

主界面

无

当你看到输出，说明启动成功

{ "code": 0, "message": "install success, only api call" }

启动方式

• 链接启动

http://127.0.0.1:8000/launcher?project=gpt_sovits

• 命令启动

uv run cli.py install -n gpt_sovits -p 8015 --start

• 原生启动

uv run api_v2_.py --bind_addr 0.0.0.0 --port 8015

输出日志

Python 3.11.11
Using extensions/gpt_sovits/.venv/scripts/python.exe
Checked 179 packages in 6ms
All installed packages are compatible
Audited 42 packages in 14ms
...
extensions/gpt_sovits/.venv/scripts/python.exe api_v2_.py --bind_addr 0.0.0.0 --port 8015
2025-12-24 00:09:50.152 | INFO  14140 cbinstaller.py:439 - ✅ gpt_sovits has started (PID: 11300)
2025-12-24 00:09:50.153 | WARNING 14140 cbinstaller.py:440 - No UI, API calls only
...
---------------------------------------------TTS Config---------------------------------------------
device              : cpu
is_half             : False
version             : v2Pro
t2s_weights_path    : GPT_SoVITS/pretrained_models/s1v3.ckpt
vits_weights_path   : GPT_SoVITS/pretrained_models/v2Pro/s2Gv2Pro.pth
bert_base_path      : GPT_SoVITS/pretrained_models/chinese-roberta-wwm-ext-large
cnhuhbert_base_path : GPT_SoVITS/pretrained_models/chinese-hubert-base
----------------------------------------------------------------------------------------------------

Loading Text2Semantic weights from GPT_SoVITS/pretrained_models/s1v3.ckpt
Loading VITS weights from GPT_SoVITS/pretrained_models/v2Pro/s2Gv2Pro.pth. <All keys matched successfully>
Loading BERT weights from GPT_SoVITS/pretrained_models/chinese-roberta-wwm-ext-large
Loading CNHuBERT weights from GPT_SoVITS/pretrained_models/chinese-hubert-base
INFO:     Started server process [12392]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:8015 (Press CTRL+C to quit)

参数配置

webapp/extensions/gpt_sovits/data/config.json

{
    "request": {
        "top_k": 5,
        "top_p": 1.0,
        "temperature": 1.0,
        "text_split_method": "cut5",
        "batch_size": 1,
        "batch_threshold": 0.75,
        "split_bucket": true,
        "fragment_interval": 0.3,
        "media_type": "wav",
        "streaming_mode": false,
        "parallel_infer": true,
        "repetition_penalty": 1.35,
        "sample_steps": 32,
        "super_sampling": false,
        "overlap_length": 2,
        "min_chunk_length": 16
    },
    "models": {
        "test": {
            "gpt": "webapp/extensions/gpt_sovits/train/weights/GPT_weights_v2Pro/test-e4.ckpt",
            "sovits": "webapp/extensions/gpt_sovits/train/weights/SoVITS_weights_v2Pro/test_e4_s80.pth"
        }
    }
}

模型训练

见《模型训练》章节

注意

• request 请求参数，models 自定义模型配置

• 在配音模块中填写本地与远程地址，可以批量语音合成，例：

  • 本地访问:http://127.0.0.1:8015
  • 远程访问 : https://xxx.gradio.live、https://xxx.ngrok-free.app、https://xxx.loca.lt
  • 属于你的公网 IP 或域名