Video Foley (MMAudio)

MMAudio v2 — generate synchronized sound (foley, ambience, impacts) FOR a video clip. Input a video + a text description of the sound; output is the same video with a matched soundtrack. Makes silent AI b-roll sound real.

Try Video Foley (MMAudio) in the playground

Last updated View as MarkdownAgent setup

Video Foley (MMAudio)

Badge: foley
Node type: audio:mmaudio_v2
Category: audio

Description

Video Foley (MMAudio) adds sound that matches the action in a video clip: wire the clip into Video, describe the sound in Sound Description, for example "footsteps on gravel, distant traffic", and run the node. It runs MMAudio v2 and returns the same video with a synchronized soundtrack of foley, ambience or impacts, which is useful for silent AI b-roll. Negative Prompt is an optional input, and the sidebar sets Duration from 1 to 30 seconds, Steps and Guidance. It costs about 1 credit per second; the Pricing section below explains how clip length changes that.

Pricing

  • Cost: ~1 credit per second
  • Per-second rate: The figure is the rate for a 5-second clip. Shorter clips can cost a bit more per second. You're always charged for the real length.

Canvas ports

These appear as port handles on the left side of the node.

ID Label Details
video_url Video VIDEO (required)
prompt Sound Description TEXT (required)
negative_prompt Negative Prompt TEXT

These render as form fields in the right-side config panel when the node is selected.

ID Label Details
duration Duration (s) NUMBER · 1…30
num_steps Steps NUMBER · 4…50
cfg_strength Guidance NUMBER · 0…20
seed Seed TEXT

Outputs

ID Label Type
video Video + Audio VIDEO

Auto-generated from the Wireflow node registry.

For AI agents: the full documentation index is at /llms.txt, and most docs pages are available as Markdown by adding .md to the URL.

© 2026 Wireflow. All rights reserved.