This document provides a comprehensive reference for the parameters available across various audio generation models in the Scenario API. Each model has a unique modelId and a set of specific parameters that can be used to control the SFX generation process. Understanding these parameters is crucial for effectively utilizing the API to achieve desired audio outputs.

Below, you will find detailed information for each audio model, including its modelId, the types of parameters it accepts, allowed values, default settings, and a clear description of each parameter's function.

Beatoven Sound Effect

Model ID: model_beatoven-sound-effect

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	–	–	–	–	Required. Describe the sound effect you want
`negativePrompt`	Negative Prompt	`string`	""	–	–	–	Describe sound qualities to avoid
`duration`	Duration	`number`	7	1	35	–	Length in seconds
`refinement`	Refinement	`number`	40	10	200	–	Higher = more refined output
`creativity`	Creativity	`number`	16	1	20	–	Higher = more imaginative interpretation
`seed`	Seed	`number`	–	0	2147483647	–	Optional reproducible generation

ElevenLabs Sound Effects v2

Model ID: model_elevenlabs-sound-effects-v2

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`text`	Sound Description	`string`	–	–	–	–	Required. Description of the sound effect (max 2048 chars)
`durationSeconds`	Duration	`number`	5	0.5	30	–	If omitted, optimal duration is auto-detected
`promptInfluence`	Guidance	`number`	0.3	0	1	–	Higher = closer to prompt, less variation
`loop`	Loop	`boolean`	false	–	–	–	Loops the generated sound
`outputFormat`	Output Format	`string`	mp3_44100_128	–	–	mp3_22050_32, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192	Codec_sampleRate_bitrate format