[GH-ISSUE #1705] Cracking sound when separating vocals and instrumentals (with back vocals) #1137

New issue

Open

opened 2026-10-20 10:06:17 +00:00 by bsakaguchi · 5 comments

bsakaguchi commented

2026-10-20 10:06:17 +00:00

Owner

Originally created by @LordMilutin on GitHub (Jan 12, 2024).
Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/1705

Hi!
I have a weird issue where I always get some cracking sound every few seconds after separating vocals and instrumental + vocals.
Cracking is present on both files.
For the track in the attachment, you can start hearing it after 00:16.
To me it sounds like bass is making a problem but I am not certain.

Lav.flac.zip

Originally created by @LordMilutin on GitHub (Jan 12, 2024). Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/1705 Hi! I have a weird issue where I always get some cracking sound every few seconds after separating vocals and instrumental + vocals. Cracking is present on both files. For the track in the attachment, you can start hearing it after 00:16. To me it sounds like bass is making a problem but I am not certain. [Lav.flac.zip](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/files/13916525/Lav.flac.zip)

bsakaguchi added the

bug

help wanted

labels

2026-10-20 10:06:17 +00:00

bsakaguchi commented

2026-10-20 10:06:18 +00:00

Author

Owner

@s1rne commented on GitHub (Jan 26, 2024):

Exactly the same problem. when using HPx_.... models. When percussion instruments (mostly kicks) are played, a sound appears on the instrumental track that reaches the volume limit, resulting in a “crackling” sound.

Because of this problem, I went to try third-party models, but ran into a problem that I described here -> #1765

@s1rne commented on GitHub (Jan 26, 2024): Exactly the same problem. when using HPx_.... models. When percussion instruments (mostly kicks) are played, a sound appears on the instrumental track that reaches the volume limit, resulting in a “crackling” sound. Because of this problem, I went to try third-party models, but ran into a problem that I described here -> #1765

bsakaguchi commented

2026-10-20 10:06:18 +00:00

Author

Owner

@LordMilutin commented on GitHub (Jan 31, 2024):

If you find a model that resolves this please let me know.

@LordMilutin commented on GitHub (Jan 31, 2024): If you find a model that resolves this please let me know.

bsakaguchi commented

2026-10-20 10:06:18 +00:00

Author

Owner

@s1rne commented on GitHub (Feb 1, 2024):

I couldn't find the model, but I was able to solve the problem with the cracks. So it turned out that the audio could have a high volume, and uvr could actually increase the volume. The result was a volume higher than maximum => crackling

In short, try reducing the volume of the audio input and the problems should go away

@s1rne commented on GitHub (Feb 1, 2024): I couldn't find the model, but I was able to solve the problem with the cracks. So it turned out that the audio could have a high volume, and uvr could actually increase the volume. The result was a volume higher than maximum => crackling In short, try reducing the volume of the audio input and the problems should go away

bsakaguchi commented

2026-10-20 10:06:18 +00:00

Author

Owner

@Zhincore commented on GitHub (Apr 20, 2024):

I have this issue with HP5_only_main_vocal model. This is how the resulting vocals look in audacity:

Right channel is totally f*cked, not only crackling

@Zhincore commented on GitHub (Apr 20, 2024): I have this issue with `HP5_only_main_vocal` model. This is how the resulting vocals look in audacity: ![image](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/assets/21307300/7127ef8b-ba20-4827-8222-50e5e0d6ea03) Right channel is totally f*cked, not only crackling

bsakaguchi commented

2026-10-20 10:06:18 +00:00

Author

Owner

@arbazw commented on GitHub (Jun 21, 2024):

Use noise reduction techniques to remove artifacts.

import noisereduce as nr

y, sr = librosa.load('your_audio_file.wav', sr=None) # Load your audio file

y_reduced = nr.reduce_noise(y=y, sr=sr) # Apply noise reduction

librosa.output.write_wav('reduce_noise.wav', y_reduced, sr) # Save the noise-reduced audio

@arbazw commented on GitHub (Jun 21, 2024): Use noise reduction techniques to remove artifacts. ``` import noisereduce as nr y, sr = librosa.load('your_audio_file.wav', sr=None) # Load your audio file y_reduced = nr.reduce_noise(y=y, sr=sr) # Apply noise reduction librosa.output.write_wav('reduce_noise.wav', y_reduced, sr) # Save the noise-reduced audio ```