#3783 videotrans.configure._except.StopRetry: Ref Audio Path & Text required in Settings

79.163* Posted at: 2 hours ago 👁5

Ref Audio Path & Text required in Settings:
Traceback (most recent call last):
File "videotrans\util\ListenVoice.py", line 16, in run
File "videotrans\tts\__init__.py", line 332, in run
File "videotrans\tts\_base.py", line 136, in run
File "videotrans\tts\_fishtts.py", line 28, in _exec
File "videotrans\tts\_base.py", line 205, in _local_mul_thread
File "videotrans\tts\_fishtts.py", line 69, in _item_task
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\_fishtts.py", line 42, in _run
videotrans.configure._except.StopRetry: Ref Audio Path & Text required in Settings

=
system:Windows-10-10.0.26200-SP0
version:v3.98
frozen:True
language:en
root_dir:D:/win-pyvideotrans-v3.98-317

1 Replies

Floor #1 DeepSeek AI reply at 2 hours ago

This error occurs because the Fish-TTS channel requires both a reference audio file and reference text to be configured in its settings when using the "clone" voice role, but they are missing.

Solution:

  1. Go to the main menu: Tools/Options -> TTS Settings.
  2. Find the Fish-TTS configuration panel.

  3. In the settings, you must provide both:

    • Reference Audio Path: The path to a short audio file (3-10 seconds) of the voice you want to clone.
    • Reference Text: The exact text spoken in that reference audio file.
  4. Fill in both fields and save the settings.
  5. If you are not trying to clone a voice, switch to a standard voice role (e.g., "Xiaoxiao" for Chinese) instead of selecting "clone".

Note: This is a common requirement for voice cloning channels (like Fish-TTS, GPT-SoVITS, CosyVoice). The reference audio should be clear speech, ideally 3-10 seconds long.

Please refer to the relevant documentation:

Post Your Reply
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.

Related resource