Sound Effects and Foley Direction

Generate film-grade sound effects with ElevenLabs SFX: source, space, and temporal shape in the 10-60 words that actually steer it.

Describe the sound in 10-60 words using this structure:

[SOURCE, the thing making the sound, with material and size: "a heavy oak door" / "a small brass bell" / "boots on wet gravel"]
+ [THE EVENT: "creaks open slowly" / "struck once, sharply" / "walking at a steady pace, passing left to right"]
+ [THE SPACE, acoustics change everything: "in a vast stone cathedral, long natural reverb" / "in a small carpeted room, dry and close" / "outdoors, open air, slight wind"]
+ [TEMPORAL SHAPE: "starts quietly and builds to a crash" / "one clean hit with a long decay" / "loops steadily for the full duration"]

Examples that work:
- "A heavy wooden ship's hull groaning and creaking under strain in rough seas, rope stretching, distant muffled waves, deep and ominous, slowly intensifying."
- "Crisp UI confirmation chime, small glass marble dropping onto a ceramic plate, bright, short decay, clean studio recording, no background noise."
- "Footsteps of one person in dry autumn leaves, unhurried walking pace, close perspective, quiet forest ambience behind, 10 seconds, even rhythm."

Onomatopoeia helps alongside description: "a deep WHOOMP as the furnace ignites, followed by a low steady roar."

Settings: set duration explicitly (up to ~30s) rather than auto when timing matters; keep the guidance/prompt-influence control low (~0.3-0.5) for creative interpretations, high for literal accuracy; always generate 3-5 variations and pick. SFX selection is a numbers game even in real foley libraries.

How to use

The space description is the most neglected lever: the same door creak reads as horror in a cathedral and as sitcom in a dry room. For layered scenes (a storm: rain bed + thunder hits + wind gusts), generate each layer as a separate effect and mix them in your editor rather than asking for the whole scene at once. Pairs naturally with AI video work: mute the generated clip's audio and rebuild the soundscape with three or four of these.

Originated fromStan SedberryUpdated
Sound designintermediate

More audio prompts

Build me a style prompt for [SUNO / UDIO / ELEVENLABS MUSIC].

What I want it to sound like: [DESCRIBE IT IN YOUR OWN WORDS, INCLUDING ARTISTS YOU HAVE IN MIND. I will translate those into describable qualities rather than using the names.]
Where it will be used: [BACKGROUND FOR A VIDEO / A SONG PEOPLE LISTEN TO / A PODCAST INTRO / A GAME

Suno Style Prompt Builder

Build a precise style field from era, instrumentation, vocals, and production instead of artist names, plus exclusions that fix a bad take.

Audiobeginner
Write a jingle for [BRAND].

What the brand does, in plain words: [ONE SENTENCE]
The one thing to remember: [THE NAME, THE OFFER, OR THE PHONE NUMBER]
Audience: [WHO]
Brand personality: [THREE WORDS]
Where it plays: [RADIO / TV / SOCIAL PRE-ROLL / IN STORE / PODCAST READ]
Lengths needed: [e.g. 5 seconds, 15 seconds, 30 seconds]
Genre and 

Brand Jingle

Write a jingle or brand anthem people remember: one hook, a name that lands on the strong beat, and versions cut for every ad length.

Audiointermediate
Direct the narration for this text.

Text to narrate:
"""
[PASTE THE CHAPTER OR SECTION]
"""

Genre: [LITERARY FICTION / THRILLER / MEMOIR / BUSINESS NONFICTION / CHILDREN'S]
Narrator: [FIRST PERSON AS THE PROTAGONIST / THIRD PERSON OMNISCIENT / THE AUTHOR READING THEIR OWN WORK]
Listener and where they listen: [e.g. "commuters, in traffi

Audiobook Narration

Direct long-form narration that stays consistent over hours: pace, character voices, pronunciation list, and chapter-level consistency notes.

Audioadvanced

Search prompts

Find a prompt by title, description, tag, or category.