Fuser

MMAudio

Provided by Fal — Learn More

MMAudio generates synchronized audio given video and/or text inputs. It can be combined with video models to get videos with audio.

Preview

Inputs

Prompt
text
Description of the audio you want to generate
Video
video
Video to generate audio from
optional: true
Negative Prompt
text
Description of sounds to avoid in the generated audio
default: noisy, low quality, low volume
Duration
number
Length of audio in seconds (between 1 and 30)
default: 5•minimum: 1•maximum: 30
Seed
seed
Random seed for reproducible results.
default: 7646
Number of Steps
number
Number of steps for the audio generation
default: 25•minimum: 4•maximum: 50
CFG Scale
number
The strength of Classifier Free Guidance.
default: 4.5•minimum: 0.1•maximum: 20
Mask Away Clip
toggle
Whether to mask away the clip.
default: false

Outputs

Audio
audio
The generated audio file
optional: true
Video
video
The generated video file
optional: true