Voice Isolator
Audio to audio model by inworld
Voice Isolator launched on 14 November 2026. It ranked #22 on Daily Launch on 20 November 2026 with a Launch Score of 63, from trending score 262 on Hugging Face. It was new in the ranking that day.
What is Voice Isolator?
Use them for cleaning recordings before playback or publication, curating speech datasets and voice pipelines where the speaker's identity must survive. With the realtime model, use them for live calls and streams. Subtract the isolated voice from the input to extract background noise or a backing-track residual for vocals/music separation.
From its model card on Hugging Face
Voice Isolator is a model by inworld on Hugging Face. It is released under the Apache 2.0 license.
How to get Voice Isolator
pip install inworld-voice-isolationFrom its model card on Hugging Face
More steps and the source are in its model card on Hugging Face.
Launch timeline
Launch Score, last 7 days
Ranked on one day so far: 63 of 100 on 20 November.
#43 of 226 in the roundup for the week of 16-22 November 2026.