GET

/v1/schemas/fal/audio/fal-ai%2Felevenlabs%2Fmusic

kind inputactivity audiohash 2c0f70aeextracted Jul 6, 2026version currentsource upstream spec ↗

Request body

6 properties · 0 required · 2 $defs
propertytypedescriptionconstraints
composition_planMusicCompositionPlanThe composition plan for the musicnullable
output_formatenumOutput 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_instrumentalbooleanIf 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_msintegerThe 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
promptstringThe text prompt describing the music to generatelength ≤ 4100 · nullable
respect_sections_durationsbooleanControls 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

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", …}]}