fal.ai·Music & sound

Stable Audio 2.5

/fal-ai/stable-audio-25/text-to-audioasync$0.3 / audio clip

Generate high quality music and sound effects using Stable Audio 2.5 from StabilityAI Returns hosted file URLs (download promptly; fal keeps them for a limited time). Billed per audio clip.

Charged per audio clip produced; a call that produces nothing is charged one unit.

Input

promptstringrequired
The prompt to generate audio from
seedany
seed
seconds_totalinteger
The duration of the audio clip to generate (default 190)
num_inference_stepsinteger
The number of steps to denoise the audio for (default 8)
sync_modeboolean
If `True`, the media will be returned as a data URI and the output data won't be available in the request history. (default false)
guidance_scalenumber
How strictly the diffusion process adheres to the prompt text (higher values make your audio closer to your prompt). (default 1)

Field	Type	Required	Description
prompt	string	yes	The prompt to generate audio from
seed	any	—	seed
seconds_total	integer	—	The duration of the audio clip to generate (default 190)
num_inference_steps	integer	—	The number of steps to denoise the audio for (default 8)
sync_mode	boolean	—	If `True`, the media will be returned as a data URI and the output data won't be available in the request history. (default false)
guidance_scale	number	—	How strictly the diffusion process adheres to the prompt text (higher values make your audio closer to your prompt). (default 1)

Run it

curl -s https://sooma.dev/v1/run \ -H "Authorization: Bearer $SOOMA_API_KEY" \ -H "Content-Type: application/json" \ -d '{"provider":"fal","endpoint":"/fal-ai/stable-audio-25/text-to-audio","input":{"prompt":"A cinematic photo of a lighthouse at dawn, soft light"}}'

Or ask your agent: it will call inspect for this schema and run it over MCP.