ElevenLabs SFX turns a description into the sound: foley and effects from one to twenty-two seconds, on demand.
ElevenLabs SFX turns descriptions into effects: “heavy wooden door slam with echo”, “retro arcade power-up”, “distant thunder rolling”. It replaces stock-library hunting for the effects that need to exist quickly.
Effects are saved to your Assets as short audio clips. Layer them on the timeline’s stacked audio lanes with clip-level volume and fades.
At a glance
Type: Sound effects from text
Duration: 1–22 seconds
Input: Plain-language description
Best for: Foley, UI sounds, impacts, ambience hits
What it is best at
Any effect you can describe in words, seconds later
No stock-library licensing to work through
Layers cleanly on stacked audio lanes
What it costs
From 1 tokens ($0.01) per clip; 2 tokens ($0.02) at the default settings.
Settings
Tokens
Price
1 s
1
$0.01
3 s
2
$0.02
5 s
2
$0.02
10 s
4
$0.04
22 s
9
$0.09
Prices come from the live catalog at $0.0100 per token, the pay-as-you-go rate; subscriptions include tokens at a lower rate. The exact price is shown before you generate, and a failed generation is refunded.
Questions
How specific can an ElevenLabs SFX description be?
Very. Material, environment, distance and character all help: “glass bottle rolling on concrete, close mic” beats “bottle sound”. Generate a few variants and keep the best.
Can ElevenLabs SFX sync sound to an existing video clip?
That is a different model. MMAudio takes your clip and generates matched sound. Use SFX for individual described effects and MMAudio for whole-clip ambience.
How is ElevenLabs SFX billed?
Per generation in tokens. Effects are among the cheapest generations in the catalog.