#7807 No audio file was generated during the listening test.self=HiggsVoice(uuid=None, proxy_str=None, last_down_time=17910644

67.68**9 Posted at: 1 hour ago

No audio file was generated during the listening test.
self=HiggsVoice(uuid=None, proxy_str=None, last_down_time=1791064467.1035028, tts_type=11, len=1, language='fr', play=True, volume='+0%', rate='+0%', pitch='+0Hz', has_done=0, wait_sec=1.0, dub_nums=1, error='No audio file was generated during the listening test.', api_url='', model_name='', is_cuda=False, local_dir=None, is_redubb=False):
{'text': "Bonjour, mon cher ami, j'espère que chacune de tes journées sera belle et agréable !", 'rate': '+0%', 'role': 'en_female_1.wav', 'filename': 'I:/Pyvideotrans/tmp/10412/listen_voice/11-fr-1791063960.6845486.wav', 'tts_type': 11, 'language': 'fr', 'volume': '+0%', 'pitch': '+0Hz'}
Traceback (most recent call last):
File "videotrans\util\ListenVoice.py", line 21, in run
File "videotrans\tts\__init__.py", line 119, in run
File "videotrans\tts\_base.py", line 123, in run
videotrans.configure.excepts.DubbingSrtError: No audio file was generated during the listening test.
self=HiggsVoice(uuid=None, proxy_str=None, last_down_time=1791064467.1035028, tts_type=11, len=1, language='fr', play=True, volume='+0%', rate='+0%', pitch='+0Hz', has_done=0, wait_sec=1.0, dub_nums=1, error='No audio file was generated during the listening test.', api_url='', model_name='', is_cuda=False, local_dir=None, is_redubb=False)

=
system:Windows-10-10.0.19045-SP0
version:v4.14
frozen:True
language:en_US
root_dir:I:/Pyvideotrans

#1 DeepSeek reply at 1 hour ago

The "No audio file was generated during the listening test" error with the Higgs-audio-v3 (HiggsVoice, tts_type=11) channel typically means the model failed to load or produce output — most commonly because the model was not fully downloaded, or your hardware (RAM/VRAM) is insufficient for this large model.

Troubleshooting steps:

Confirm/redownload the model manually. Higgs-audio-v3 requires all files from https://huggingface.co/multimodalart/higgs-audio-v3-tts-4b-transformers/tree/main, placed in I:/Pyvideotrans/models/models--multimodalart--higgs-audio-v3-tts-4b-transformers.

Auto-download failures are very common; delete the folder and redownload if incomplete.
Check hardware requirements. Higgs-audio-v3 needs >10 GB VRAM for GPU acceleration, or ~20 GB system RAM if running on pure CPU (is_cuda=False in your log means CUDA was not used).

Low memory will silently produce no audio.
Enable CUDA acceleration if you have an NVIDIA card (CUDA 12.8 + cuDNN 9.11), or free up memory.
Check the log file at I:/Pyvideotrans/logs/ (latest date) for deeper model-loading errors.

If the above does not resolve it, or you simply need reliable French TTS, switch the TTS channel to Edge-TTS (free), which supports French with no model download or heavy hardware requirements.

#7807 No audio file was generated during the listening test.self=HiggsVoice(uuid=None, proxy_str=None, last_down_time=17910644

1 Replies

Please refer to the relevant documentation:

Post Your Reply

Related resource