GET

/v1/schemas/fal/audio/fal-ai/elevenlabs/music

Accept:

kind inputactivity audiohash 43170308…extracted Nov 8, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `5b323702b8a9c966053d921a8d8fa12a2361f2528689abc665ce06fe4117d88a` { "fetchedAt": 1794114001, "extractorVersion": "2", "verifiedAt": null }

Request body

7 properties · 0 required · 2 $defs

property	type	description	constraints
enable_safety_checker	boolean	Check input content for safety. Disabling requires account authorization.	default: true
composition_plan	MusicCompositionPlan	The composition plan for the music	nullable
respect_sections_durations	boolean	Controls how strictly section durations in the composition_plan are enforced. It will only have an effect if it is used with composition_plan. When set to true, the model will precisely respect each section's duration_ms from the plan. When set to false, the m…	default: true
output_format	enum	Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample …	mp3_22050_32 \| mp3_44100_32 \| mp3_44100_64 \| mp3_44100_96 \| mp3_44100_128 \| mp3_44100_192 · +13 more · default: "mp3_44100_128"
force_instrumental	boolean	If true, guarantees that the generated song will be instrumental. If false, the song may or may not be instrumental depending on the prompt. Can only be used with prompt.	default: false
music_length_ms	integer	The length of the song to generate in milliseconds. Used only in conjunction with prompt. Must be between 3000ms and 600000ms. Optional - if not provided, the model will choose a length based on the prompt.	3000 ≤ n ≤ 600000 · nullable
prompt	string	The text prompt describing the music to generate	length ≤ 4100 · nullable

Types

2 $defs

MusicCompositionPlanobject

sections*	MusicSection[]	The sections of the song.
positive_global_styles*	string[]	The styles that should be present in the entire song.
negative_global_styles*	string[]	The styles that should not be present in the entire song.

MusicSectionobject

lines*	string[]	The lyrics of the section. Each line must be at most 200 characters long.
negative_local_styles*	string[]	The styles that should not be present in this section.
section_name*	string	The name of the section. Must be between 1 and 100 characters.	length ≥ 1 · length ≤ 100
duration_ms*	integer	The duration of the section in milliseconds. Must be between 3000ms and 120000ms.	3000 ≤ n ≤ 120000
positive_local_styles*	string[]	The styles that should be present in this section.

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/elevenlabs/music","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}