Input example
Close footsteps on wet pavement, light rain behind them, no speech or music.
Generated sound effect versions to audition and download.
Listen to the existing generated examples in the workspace, then try a focused brief of your own.
A CLOSER LOOK
Describe a sound for your scene, then compare generated takes before placing one in your edit.
Generate sound effects from text. Describe a sound, choose a single sound or loop, then listen to the returned versions and download your preferred take.
Create a sound effect from words: footsteps on wet pavement, rain against a window or a short percussion pattern. Name the source, its surroundings and the texture you want. For a video edit, describe the sound itself rather than asking for an entire finished soundtrack.
A focused brief makes the returned versions easier to compare. Specify a close or distant sound, a dry or reverberant space, and whether other sounds should stay in the background. Listen to the existing examples above for possible directions.
Select Single sound for a self-contained sound or Loop for audio intended to repeat. A door closing, a transition cue and a rhythmic bed have different jobs in an edit. Keep the prompt consistent with the selected sound type.
The current generator sets duration automatically. There is no exact-length control on this page. Review the displayed credit cost before submission, then trim or place the downloaded audio in your editor when precise timing is needed.
Listen to every returned version before choosing a take. Check the start, decay, background texture and any unwanted speech or music. For a loop, audition repeated playback to hear whether the join works for your scene.
Download the take you want to use and check its level alongside dialogue and music in your editor. Generating a sound does not automatically insert it into a video or synchronize it to a timeline.
Name the sound source, setting and texture. Focus the prompt on the sound you want to hear.
Use a one-shot for a standalone sound or a loop for repeating audio. The duration is set automatically; review the displayed credit cost.
Compare the returned versions. Check the attack, ending and, for loops, the join before adding the sound to your edit.
Close footsteps on wet pavement, gentle rain in the background, a quiet street, no speech or music.
Choose Single sound and compare the footstep detail and surrounding ambience.
A minimal percussion loop, warm kick, dry handclaps and crisp shakers, steady groove, no melody or singing.
Choose Loop and check the join during repeated playback.
No audio upload is required. Describe the sound in words and choose Single sound or Loop. To clean an existing spoken recording, choose Clean voice instead.
Duration is set automatically by the current generator. Use your audio or video editor to trim the downloaded result or place it at an exact time.
Single sound requests a standalone sound; Loop requests repeating audio. Listen to the actual result, especially the join during repeated playback, before using it in a production.
Review the credit cost displayed for the selected model and output settings before submitting. Available controls, limits and prices depend on that selection. You can prepare the inputs before signing in; submission requires the account and credit checks shown by the workspace.
Use material you own or have permission to transform and review the applicable service and model terms. Inspect the entire returned file before publishing. Download the results you want to keep; do not treat temporary access or a saved task record as a promise of permanent file storage.