#8256 Dubbing failed{

85.232**1 Posted at: 1 hour ago

Dubbing failed{"detail":"Not Found"}
self.api_url='http://127.0.0.1:9874/tts'
self.model_name=''
self=[GPTSoVITS]: uuid='091603ddbc', proxy_str=None, tts_type=13, len=65, language='ru', play=False, volume='+100%', pitch='+0Hz', rate='+0%', speed=1.0, has_done=0, wait_sec=1.0, dub_nums=1, error='{"detail":"Not Found"}\nself.api_url=\'http://127.0.0.1:9874/tts\'', api_url='http://127.0.0.1:9874/tts', is_cuda=True, local_dir=None, is_redubb=False, model_name='', ainame=None
Traceback (most recent call last):
File "videotrans\task\only_one.py", line 108, 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 132, in run
File "videotrans\tts\_base.py", line 140, in run
videotrans.configure.excepts.DubbingSrtError: Dubbing failed{"detail":"Not Found"}
self.api_url='http://127.0.0.1:9874/tts'
self.model_name=''
self=[GPTSoVITS]: uuid='091603ddbc', proxy_str=None, tts_type=13, len=65, language='ru', play=False, volume='+100%', pitch='+0Hz', rate='+0%', speed=1.0, has_done=0, wait_sec=1.0, dub_nums=1, error='{"detail":"Not Found"}\nself.api_url=\'http://127.0.0.1:9874/tts\'', api_url='http://127.0.0.1:9874/tts', is_cuda=True, local_dir=None, is_redubb=False, model_name='', ainame=None

trk=[TransCreate]: uuid='091603ddbc', proxy_str=None, cfg=[TaskCfgVTT]当前工作模式: 翻译视频单视频模式
原始输入文件名: D:/2_УРОКИ ПО FotoFusion/00_НЕЙРОСЕТЬ/000_Capture One Pro/000_Курс «Захвати одного эксперта»/videos/Solution to Image Editing Practice 9.mp4,
输出结果保存到文件夹: D:/2_УРОКИ ПО FotoFusion/00_НЕЙРОСЕТЬ/000_Capture One Pro/000_Курс «Захвати одного эксперта»/Lesson RU/Solution to Image Editing Practice 9-mp4,
临时文件夹: D:/pyVideoTrans/tmp/4128/091603ddbc
已选清理已存在
已启用CUDA加速
未选降噪
已选识别说话人，最大说话人数量不限制
Сервис STT (распознавание):faster-whisper(Built-in), large-v3-turbo, 发音语言: en, LLM纠错
Канал перевода:DeepSeek,原始语言:en,目标语言:ru, 已选 Отправить полный SRT
Канал озвучки (TTS):GPT-SoVITS(LocalAPI), 角色:clone, 配音语言:ru, 未选二次语音识别
音量:+100%, 语速:+0%, 已选音频加速, 已选视频慢速
已选移除每条字幕配音开头和结尾静音缓冲
静音移除力度: default
字幕: nosubtitle , precent=18, hasend=False, should_recogn=True, should_trans=True, should_dubbing=True, should_hebing=True, is_copy_video=True, video_codec_num=264, ignore_align=False, is_audio_trans=False, clone_ref='', should_recogn2=False, do_diarize=True
video_duration_ms=437560

=
system:Windows-10-10.0.19045-SP0
version:v4.16
frozen:True
language:ru
root_dir:D:/pyVideoTrans

#1 DeepSeek reply at 1 hour ago

This is not a pyVideoTrans bug. The address you entered for GPT‑SoVITS does not match an existing API endpoint: GPT‑SoVITS returned 404 Not Found, which means the service received the request but no /tts route exists at that host and port (or the service is not running / is running the WebUI rather than the API).

Check these in order:

Remove the path, keep only the base address. In Menu → TTS Settings → GPT-SoVITS, the field must contain only the service root, e.g. http://127.0.0.1:9880 — do not append /tts. The program builds the /tts request path itself, so what you entered becomes /tts/tts → Not Found.
Confirm the port. 9874 is not the default GPT‑SoVITS API port (9880). If you really launched the API on a custom port, use that exact port — but make sure it is the API process, not the WebUI (7860). Entering the WebUI address is one of the most common causes of this error.
Match the API version checkbox. If you started api.py (v1) but the software's api_v2? option is ticked (or the reverse), the request path differs and you get {"detail":"Not Found"}. Tick/untick it to match the script you actually launched, then restart the GPT‑SoVITS service.
Verify the service is alive. Before re-running, open a browser and confirm the API is listening (the terminal of api.py/api_v2.py shows the bound port; no error/warning about missing pretrained models).
Do not route it through the proxy — local services are bypassed automatically, but an invalid proxy in the proxy box will break localhost calls too. Clear the proxy field if it is filled.

Additional problem — the target language is unsupported. Your task config shows 配音语言: ru, but GPT‑SoVITS is designed for 中/英/日/韩/粤 only; it does not support Russian. Even after fixing the URL, dubbing into Russian with this channel will fail or produce garbage. Switch the TTS channel for this job to a Russian-capable one, e.g. OmniVoice-TTS, Qwen3-TTS, Confucius-TTS, Higgs-audio-v3, or Edge-TTS.

After changing the settings, tick 清理已生成(Clear Output) before re-running, so the failed dubbing cache from the previous attempt is discarded and not reused.

#8256 Dubbing failed{

1 Replies

Please refer to the documentation:

Post Your Reply

Related resource