#7231 cosyvoice Service must be deployed and running before useself.api_url='http://127.0.0.1:8000'

103.29**5 Posted at: 1 hour ago

cosyvoice Service must be deployed and running before use
self.api_url='http://127.0.0.1:8000'
[WinError 10061] No connection could be made because the target machine actively refused it

Traceback (most recent call last):
File "httpx\_transports\default.py", line 101, in map_httpcore_exceptions
File "httpx\_transports\default.py", line 250, in handle_request
File "httpcore\_sync\connection_pool.py", line 216, in handle_request
File "httpcore\_sync\connection_pool.py", line 196, in handle_request
File "httpcore\_sync\connection.py", line 99, in handle_request
File "httpcore\_sync\connection.py", line 76, in handle_request
File "httpcore\_sync\connection.py", line 122, in _connect
File "httpcore\_backends\sync.py", line 205, in connect_tcp
File "contextlib.py", line 153, in exit
File "httpcore\_exceptions.py", line 14, in map_exceptions
httpcore.ConnectError: [WinError 10061] No connection could be made because the target machine actively refused i
......
ll 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\_cosyvoice.py", line 37, in _run
File "tenacity\__init__.py", line 338, in wrapped_f
File "tenacity\__init__.py", line 477, in call
File "tenacity\__init__.py", line 378, in iter
File "tenacity\__init__.py", line 400, in
File "concurrent\futures\_base.py", line 451, in result
File "concurrent\futures\_base.py", line 403, in __get_result
File "tenacity\__init__.py", line 480, in call
File "videotrans\tts\_gradio.py", line 76, in _send
videotrans.configure.excepts.StopTask: cosyvoice Service must be deployed and running before use
self.api_url='http://127.0.0.1:8000'
[WinError 10061] No connection could be made because the target machine actively refused it

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/SF/Videos/Renegade Immortal Battle of Gods Episode 1.mp4,
输出结果保存到文件夹: C:/Users/SF/Videos/_video_out/Renegade Immortal Battle of Gods Episode 1-mp4,
临时文件夹: C:/Users/SF/Downloads/Compressed/win-pyvideotrans-v4.11/tmp/12832/026c21526a
已选 清理已存在
未启用CUDA加速
未选 降噪
STT Service:faster-whisper(Built-in), large-v3-turbo, 发音语言: Simplified Chinese, 断句方式:默认断句
TranslateSrt:Microsoft Translate (Free),原始语言:Simplified Chinese,目标语言:Hindi, 已选 SendSRT
TTS Service:CosyVoice(LocalAPI), 角色:clone, 配音语言:Hindi, 已选 二次语音识别
音量:+0%, 语速:+0%, 未选 音频加速, 未选 视频慢速
未选 移除字幕间空隙, 未选 强制对齐字幕和声音
字幕: No Subtitles

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

1 Replies

#1 DeepSeek reply at 1 hour ago

This is not a bug in pyVideoTrans. The error [WinError 10061] No connection could be made because the target machine actively refused it means no CosyVoice service is running at http://127.0.0.1:8000. The CosyVoice channel is a "Local API" channel — pyVideoTrans only sends requests to a CosyVoice service that you must deploy and start yourself. The connection is refused because nothing is listening on port 8000.

Solutions (do one of the following):

  1. Deploy and start CosyVoice locally (required if you want to keep using the CosyVoice channel).

    • Clone and set up the CosyVoice project from its official repository.
    • Start its API/Gradio service so that it listens on http://127.0.0.1:8000.
    • Verify it works: open http://127.0.0.1:8000 in your browser. If the page/schema loads, the service is up. Then re-run the task in pyVideoTrans.
    • If your CosyVoice service runs on a different port, open Menu -> TTS Settings -> CosyVoice and change the API address accordingly (do NOT use 0.0.0.0; use 127.0.0.1).

  2. Don't want to deploy CosyVoice? Switch to another dubbing channel. For Hindi voice cloning, choose a channel that supports cloning and Hindi without a separate deployment, for example:

    • OmniVoice-TTS (Built-in) — supports 600+ languages including Hindi, supports clone.
    • Qwen-TTS (Built-in) or the cloud Qwen-TTS (bailian).
    • Edge-TTS (Free) if you don't need cloning (pick a Hindi voice like hi-IN-MadhurNeural).

Also note on your current task config:

  • Your target language is Hindi, but you selected the CosyVoice channel, which officially supports Chinese, English, Japanese, Korean, German, Spanish, French, Italian and Russian — Hindi is not in that list. Even with the service running, Hindi dubbing via CosyVoice will likely fail. Prefer OmniVoice-TTS or an online TTS that supports Hindi.
  • You selected the clone role. Clone requires the original video's audio to be clipped into 3–10s reference clips. Make sure in Menu -> Tools -> Advanced Options -> ASR Settings that min speech duration is around 3000–4000 ms, otherwise cloning will frequently error.

请查阅相关文档：

Thinking...
Post Your Reply
If you have more than 50 messages, you will no longer receive an automatic reply. Please ask a new question!
Open source and free maintenance is not easy. If this project is helpful to you, please consider making a small donation to help the project continue to maintain and update.

Dondate via ko-fi.com

Related resource