VRGDG_CreateSilentAudio

VRGDG_CreateSilentAudio does exactly what its name says: it outputs an audio track that's silent. No inputs, no knobs, no settings - you drop it in, it hands you an AUDIO-type output, and that's the entire node. It looks like a placeholder, and in a sense it is, but it exists to solve a real problem in the pack's LTX-2.3 music-video workflow.

Why silent audio is a feature

LTX-2 and LTX-2.3 generate video and audio together, which is great until you have a scene with no lyrics, an intro with just music, or a gap between verses. The workflow needs something to feed the audio conditioning at those points, and silence is the honest answer - it keeps the timeline full and the video chunks aligned without sneaking in noise or phantom vocals. This node is the "no audio here, but don't break the sync" token. Wire its output anywhere the graph expects audio and you want exactly nothing.

That's also its main limitation: it's fixed silence with no length control. If you need a three-second gap and the node outputs a different duration, you can't dial it in here - you'd stretch, trim, or combine it downstream. Treat it as a utility token, not a timeline editor.

Using it

There's nothing to configure, so "using" it means deciding where to hang it. In the VRGDG pipeline it slots into the same audio-shaped inputs as real audio (the AUDIO type), and it's the kind of node that makes a shared workflow reproducible - someone can load the graph with no music file attached and still run the structure end to end.

It installs with the rest of the pack:

cd ComfyUI/custom_nodes
git clone https://github.com/vrgamegirl19/comfyui-vrgamedevgirl

or via ComfyUI Manager (search "vrgamedev"), then restart. The pack's requirements.txt lists librosa and imageio, which are the audio-adjacent dependencies worth having if you're poking at the audio side of these workflows at all.

The honest verdict

This is a one-trick utility node, and it's fine that it is. You'll never build a workflow around it, but when you need a silent audio slot it's faster than assembling one from parts, and it keeps the author's music-video graphs self-contained. If you're not running an audio+video model like LTX-2, you probably don't need it at all - but if you are, this little nothing-node saves you from the alternative, which is a silent audio file you have to generate, save, and load by hand.