Generate
Back to Models
Models/elevenlabs/modelPass-through

ElevenLabs Sound Effects v2

ElevenLabs SFX v2 generates a sound effect from a written description, so a cue can be made to fit the scene rather than found in a library. On MachGen it takes up to 1,000 characters and renders 0.5 to 30 seconds, with a prompt-influence control trading literal adherence against interpretive range, and an optional seamless loop for ambience.

Current MachGen support
Sound Effects0.5-30s output1,000 characters per request
Starting at $0.002 / output s
All supported sizes$0.002/s
Live public pricebookSee full pricebook
Overview

ElevenLabs Sound Effects v2

ElevenLabs SFX v2 generates a sound effect from a written description, so a cue can be made to fit the scene rather than found in a library. On MachGen it takes up to 1,000 characters and renders 0.5 to 30 seconds, with a prompt-influence control trading literal adherence against interpretive range, and an optional seamless loop for ambience.

ElevenLabs Sound Effects v2 API on MachGen. Compare supported generation modes, examples, and current pricing from the live pricebook.

Model guide

Why choose ElevenLabs Sound Effects v2

Key strengths

  • Foley and designed effects from a plain description, with no sample library to search.
  • Explicit control over clip length, so an effect can be cut to a shot instead of trimmed after.
  • Seamless looping for ambience beds that need to run under a whole scene.

Good fit for

  • Impacts, whooshes, UI feedback, and creature or machine sounds.
  • Room tone and ambience beds for a location.
  • Placeholder audio while a scene is still being cut.
Supported on MachGen

Inputs and output settings

This table reflects the model routes and controls currently exposed by MachGen.

ModeRequired inputAvailable settings
Sound EffectsText prompt describing the effect, plus a lengthLength: 0.5-30s
Prompt limit: 1,000 characters
Workflow

Using ElevenLabs Sound Effects v2

  1. Choose a supported generation mode in Playground.
  2. Add the required prompt and source or reference assets.
  3. Select output settings from the controls shown for that mode.
  4. Generate, then inspect the returned asset before reusing the settings through the API.
Best results

How to get better ElevenLabs Sound Effects v2 results

  • Describe the source, the material, and the space - 'wooden door, heavy, in a stone hallway' beats 'door sound'.
  • Ask for one event per generation; layer several clips instead of describing a whole scene at once.
  • Turn on looping for ambience, off for one-shot events.
  • Raise prompt influence for a literal reading, lower it for a more interpretive one.
Limits

Limits and availability

  • MachGen admits only the modes and settings listed above for this catalog model.
  • Source assets must finish uploading before a request can be submitted.
  • Generated results can vary between requests, including when the same prompt and settings are reused.
  • ElevenLabs Sound Effects v2 is pass-through. MachGen sends the request through its upstream provider integration and returns the generated asset.
Learn more

Learn more

For model background, technical details, and architecture, see the official ElevenLabs sound effects guide.

Try this model in the MachGen Playground.

Official documentation may describe capabilities or parameters that are not currently exposed by MachGen. Use the Inputs and output settings section above as the source of truth for this page.

Pricing

ElevenLabs Sound Effects v2 pricing

See Pricing for currently published MachGen rates. When available, the Playground estimate reflects the selected task and output settings.

On MachGen

ElevenLabs Sound Effects v2 on MachGen

Deployment: Pass-through. ElevenLabs Sound Effects v2 is pass-through. MachGen sends the request through its upstream provider integration and returns the generated asset.

The Playground and API sections on this page list the inputs and output settings exposed for this model.