Arnndn

Audio Single output Transform

Reduce noise from speech using Recurrent Neural Networks.

FFmpeg filter: arnndn — the official reference.

Add it to a graph. The explicit form works for every filter — bind it to its input and read the result from outputs():

$node   = $audio->addFilter(new Arnndn(…));
$result = $node->outputs()[0];

Shorthand. Single-output filters can skip the node — apply() returns the result stream directly:

$result = $audio->apply(new Arnndn(…));

When to use it

TODO — when this filter shines: what it’s the right tool for, what to reach for instead when it isn’t, and how it composes with neighbouring filters.

How to use it

TODO — prose: how the filter actually works and what its key parameters mean (the explanation FFmpeg’s terse option help omits).

Examples

TODO — runnable PHP, with the equivalent ffmpeg CLI alongside.

Gotchas

TODO

See also

TODO

Parameters

Parameter	Type	Default	Range / values	Description
model	string	—	—	set model name
mix	float	1	-1–1	set output vs input mix

FFmpeg also names these options (use the parameter shown above): m → model.

---

Maps to FFmpeg’s arnndn filter. Verified against ffmpeg n7.1.1.