anira-project/anira

an architecture for neural network inference in real-time audio applications

45
/ 100
Emerging

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.

audio-plugins digital-audio-workstations real-time-audio-processing audio-effects sound-synthesis
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

209

Forks

9

Language

C++

License

Apache-2.0

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.