TSTsarp·May 4, 2026
RNNoise has a VAD inbuilt that works much better than silero.
https://github.com/xiph/rnnoise
In Show HN: Apple's SHARP running in the browser via ONNX runtime webxiph
rnnoise
C2021–2026
xiph / rnnoise
rnnoise
Recurrent neural network for audio noise reduction
8Distinct people
10Mentions
0Explicit recommenders
6KGitHub stars
What to know before exploring
What it is
Recurrent neural network for audio noise reduction
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by year10 dated mentions
Observed mentions: 2021-01-15 03:25:11 UTC to 2026-05-04 02:22:25 UTC.
* An incomplete calendar period is marked with an outlined bar. Its count is not directly comparable with a full period.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| 2021 | 2021-01-01 00:00:00 UTC | 2022-01-01 00:00:00 UTC | 2 | 0 | 2 |
| 2022 | 2022-01-01 00:00:00 UTC | 2023-01-01 00:00:00 UTC | 2 | 1 | 1 |
| 2023 | 2023-01-01 00:00:00 UTC | 2024-01-01 00:00:00 UTC | 1 | 0 | 1 |
| 2024 | 2024-01-01 00:00:00 UTC | 2025-01-01 00:00:00 UTC | 3 | 1 | 2 |
| 2025 | 2025-01-01 00:00:00 UTC | 2026-01-01 00:00:00 UTC | 1 | 0 | 1 |
| 2026 (partial) | 2026-01-01 00:00:00 UTC | 2027-01-01 00:00:00 UTC | 1 | 0 | 1 |
What Hacker News says
10 sourcesWonder if these are open models like RNNoise now is.
https://github.com/xiph/rnnoise
In OpenVINO AI effects for AudacityIt has been done before, for eg the original RNNoise was trained on proprietary data, later there was crowd-sourced effort to record new data and have it under libre licenses.
https://github.com/xiph/rnnoise/
In Codeberg Reconsidering OSI License Approval in Terms of UseThis reminds me a lot of https://github.com/xiph/rnnoise and my use of it locally. It zeroes in on voice via RNN which seems to beat most other noise detection filters I've tried. Unfortunately, I mostly disable it these days since it's a bit harder to tune than I'm up for, but it's by far the most promising local noise reduction I've used.
In AI headphones let wearer listen to a single person in a crowd by looking at themRNNoise 0.2 – now trained using only publicly available CC-licensed datasets
3 points · Open discussionSure.
Carla: https://github.com/falkTX/Carla
It lets me install any normal audio pro audio plugins, for example https://github.com/xiph/rnnoise
It also does some cable management, but qpwgraph is maybe better for that.
I looked at your code and the approach (IMO) is kind of bad.
If you want to solve the problem of "voice changer", you can skip the UI entirely and just use plugin parameters. You can also skip the problem of managing the connections. And when you publish your work, every pro audio software (Ableton, Reaper, whatever) can use your audio processing.
Hope that helps.
In Lyrebird the Linux voice changer now supports PipeWireOBS ships with rnnoise, which is like NVIDIA Broadcast, but works on any CPU. See also NoiseTorch and EasyEffects if you're on Linux.
It's pretty great, works decently, but the sad thing is the author put it out a few years ago, trained it on proprietary datasets, wrote a paper and then moved onto something else, never to be seen again. Now it's pretty much unmaintained since it requires some very specific ML and DSP knowledge to hack on.
https://github.com/xiph/rnnoise
NVIDIA Broadcast in my opinion is better, but rnnoise will do if you can't run it.
In OBS – Open Broadcaster SoftwareRecurrent neural network for audio noise reduction
4 points · Open discussionThere is training instructions in the repository. The training scripts appear to be using some pretty standard ML libraries (I'm seeing keras and mentions of tensorflow), so I imagine that the requirements are the same as those.
I don't feel I'm qualified to elaborate on this specifically, again, I'm no ML person. For more info look here:
https://github.com/xiph/rnnoise/tree/master/training
https://github.com/xiph/rnnoise/blob/master/TRAINING-README
In Show HN: Alsa_rnnoise – RNNoise-based noise removal plugin for ALSAYou can use webRTC VAD or the VAD from RNNoise.
https://github.com/xiph/rnnoise
In Ask HN: What are you working on?