TRStart creating
Menu

Stable Audio 3 Small Sfx

Stable Audio 3 Small SFX is a 459 million parameter latent diffusion model that generates high-quality sound effects from text prompts, designed for on-device deployment on mobile phones and consumer laptops.

Input

Fields marked * are required. Review the price before generating.

Duration of the generated audio in seconds.

Text description of the audio to generate.

Additional settings

Text description of qualities to avoid in the output.

Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher.

Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints.

Random seed for reproducible outputs. Omit for a random seed.

If True, the prompt will be expanded using an LLM for more detailed and higher quality results.

Container format for the generated audio output.

Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).

Price$0.04 / run

You sign up first. Your settings are kept.

API code for this input

Complete the required fields and fix input errors to see API code.

How to use Stable Audio 3 Small Sfx

Getting started

Create, transform, repair or extend sound effects with Stable Audio 3 Small Sfx.

Review your result

Listen to the complete output, including edit boundaries, stereo balance, noise and the ending.

Inputs and settings

Text mode takes prompt and duration from 1 to 120 seconds. Audio-to-audio also takes an uploaded audio_url and init_noise_level.

Inpainting replaces only mask_start_seconds to mask_end_seconds; the end must follow the start and stay within the uploaded source.

Outpainting needs a positive extend_seconds_before or extend_seconds_after. Raywake checks that the source and extensions fit within 120 seconds.

Choose MP3, WAV, FLAC, OGG, Opus, M4A or AAC. Bitrate applies to compressed formats; base checkpoints expose guidance and more sampling steps.

We use analytics cookies. Privacy policy