NeuralRack v0.4.1 bug fix release

Hermann Meyer <brummer--S0/[email protected]> Mon, 3 Aug 2026 17:24:06 +0200
Newsgroups gmane.linux.audio.devel,gmane.linux.audio.users
Message-ID <[email protected]>
NeuralRack is a Neural Model and Impulse Response File loader for=20
Linux/Windows available as Stand alone application, and in the Clap,=20
LV2, vst2 and vst3 plugin format.
It supports [*.nam files](https://www.tone3000.com/search?tags=3D103) and,=
=20
or [*.json or .aidax files](https://www.tone3000.com/search?tags=3D23562)=
=20
by using the [NeuralAudio](https://github.com/mikeoliphant/NeuralAudio)=20
engine.

For Impulse Response File Convolution it use=20
[FFTConvolver](https://github.com/HiFi-LoFi/FFTConvolver)

Resampling is done by=20
[Libzita-resampler](https://kokkinizita.linuxaudio.org/linuxaudio/zita-res=
ampler/resampler.html)

New in this release:
- fix clap plugin crash in Bitwig

Neuralrack allow to load up to two model files and run them serial.
The input/output could be controlled separate for each model.
For tone sharping a 6 band EQ could be enabled.
Additional it allow to load up a separate Impulse Response file for each=
=20
output channel (stereo).
Neuralrack provide a buffered Mode which introduce a one frame latency=20
when enabled.
It could move one Neural Model, or the complete processing into a=20
background thread. That will reduce the CPU load when needed.
The resulting latency will be reported to the host so that it could be=20
compensated.

Project Page:

https://github.com/brummer10/NeuralRack

Release Page:

https://github.com/brummer10/NeuralRack/releases/tag/v0.4.1