#7075 [GPT-SoVITS] Service must be deployed and running before use

2401**ec17 Posted at: 2 hours ago

[GPT-SoVITS] Service must be deployed and running before use

Traceback (most recent call last):
File "urllib3\connection.py", line 198, in _new_conn
File "urllib3\util\connection.py", line 85, in create_connection
File "urllib3\util\connection.py", line 73, in create_connection
ConnectionRefusedError: [WinError 10061] No connection could be made because the target machine actively refused it

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "urllib3\connectionpool.py", line 787, in urlopen
File "urllib3\connectionpool.py", line 493, in _make_request
File "urllib3\connection.py", line 494, in request
File "http\client.py", line 1278, in endheaders
File "http\client.py", line 1038, in _send_output
File "http\client.py", line 976, in send
File "urllib3\connection.py", line 325, in connect
File "urllib3\connection.py", line 213, in _new_conn
urllib3.exceptions.NewConnectionError: : Failed
......
un
File "requests\api.py", line 115, in post
File "requests\api.py", line 59, in request
File "requests\sessions.py", line 589, in request
File "requests\sessions.py", line 703, in send
File "requests\adapters.py", line 677, in send
requests.exceptions.ConnectionError: HTTPConnectionPool(host='127.0.0.1', port=9880): Max retries exceeded with url: /tts (Caused by NewConnectionError(': Failed to establish a new connection: [WinError 10061] No connection could be made because the target machine actively refused it'))

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "videotrans\task\only_one.py", line 107, in run
File "videotrans\task\_stage_dubbing.py", line 24, in dubbing
File "videotrans\task\_stage_dubbing.py", line 101, in _tts
File "videotrans\tts\__init__.py", line 233, in run
File "videotrans\tts\_base.py", line 103, in run
File "videotrans\tts\_base.py", line 206, in _exec
File "videotrans\tts\_base.py", line 166, in _local_mul_thread
File "videotrans\tts\_base.py", line 218, in _item_task
File "videotrans\tts\_gptsovits.py", line 82, in _run
videotrans.configure.excepts.StopTask: [GPT-SoVITS] Service must be deployed and running before use

cfg=[TaskCfgVTT]当前工作模式: 翻译视频单视频模式
原始输入文件名: C:/Users/JAIVA/Downloads/Video Project 15.mp4,
输出结果保存到文件夹: C:/Users/JAIVA/Downloads/_video_out/Video Project 15-mp4,
临时文件夹: C:/Users/JAIVA/Downloads/win-pyvideotrans-v4.11/tmp/21900/d2382da41c
已选清理已存在
已启用CUDA加速
未选降噪
STT Service:faster-whisper(Built-in), large-v3-turbo, 发音语言: Spanish (Latin America), 断句方式:默认断句
TranslateSrt:Google Translate (Free),原始语言:Spanish (Latin America),目标语言:English, 已选 SendSRT
TTS Service:GPT-SoVITS(LocalAPI), 角色:clone, 配音语言:English, 未选二次语音识别
音量:+0%, 语速:+0%, 已选音频加速, 未选视频慢速
字幕: No Subtitles

=
system:Windows-10-10.0.26200-SP0
version:v4.11
frozen:True
language:en
root_dir:C:/Users/JAIVA/Downloads/win-pyvideotrans-v4.11

#1 DeepSeek reply at 2 hours ago

This is caused by the GPT-SoVITS API service not running on port 9880. pyVideoTrans cannot connect to 127.0.0.1:9880 because the service is either not started, running on a different port, or the address configured in the software is incorrect.

Resolve it as follows:

First, start the GPT-SoVITS API service (not the WebUI). In the GPT-SoVITS root directory, run:
```
python api.py
```
Do NOT run webui.py — the WebUI runs on port 7860, but pyVideoTrans needs the API on port 9880.
Verify the service is actually listening on port 9880. Open a browser and visit http://127.0.0.1:9880/docs (or http://127.0.0.1:9880/). If you see a page, the service is up. If the page fails to load, the service is not running correctly.
Check the API version match in pyVideoTrans. GPT-SoVITS has api.py (v1) and api_v2.py (v2). If you started api.py, make sure the software is NOT checked with api_v2? in the GPT-SoVITS settings. If you started api_v2.py, then api_v2? MUST be checked. An incorrect match will cause requests to fail.
Confirm the API address is correct. In pyVideoTrans, go to 菜单 → TTS设置 → GPT-SoVITS and ensure the address is http://127.0.0.1:9880/ (not the WebUI 7860 port).
When using the clone voice role with GPT-SoVITS, reference audio must be placed in the GPT-SoVITS software root directory, not in pyVideoTrans' f5-tts folder.

Special note for clone in GPT-SoVITS: the reference audio is automatically cut from the original video segment. Ensure the cut segment is 3–10 seconds long, or the cloning will fail. In 高级选项 → 语音识别参数, set 最长语音持续 to 6–10 seconds and 最短语音持续 to 3000–4000 ms.

If the above is all correct and the error persists, please provide the GPT-SoVITS console output and your pyVideoTrans log file from logs/ directory for further diagnosis.

#7075 [GPT-SoVITS] Service must be deployed and running before use

1 Replies

Post Your Reply

Related resource