anira-project/anira
an architecture for neural network inference in real-time audio applications
This is a high-performance library that helps audio application developers integrate neural network models directly into their real-time audio workflows. It takes your pre-trained neural network models (e.g., for noise reduction, effects, or synthesis) and your audio input, then outputs processed audio with minimal delay. This is for audio software engineers, DSP developers, or plugin creators building applications where immediate audio feedback is crucial.
209 stars.
Use this if you are building audio applications, like VST3 or CLAP plugins, and need to embed neural network inference with guaranteed real-time performance and low latency.
Not ideal if you are not developing audio software or do not require real-time, low-latency neural network inference.
Stars
209
Forks
9
Language
C++
License
Apache-2.0
Category
Last pushed
Feb 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/anira-project/anira"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
iver56/audiomentations
A Python library for audio data augmentation. Useful for making audio ML models work well in the...
Rikorose/DeepFilterNet
Noise supression using deep filtering
torchsynth/torchsynth
A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.
marl/openl3
OpenL3: Open-source deep audio and image embeddings
archinetai/audio-data-pytorch
A collection of useful audio datasets and transforms for PyTorch.