GET

/v1/schemas/fal/audio/fal-ai%2Face-step%2Faudio-to-audio

kind inputactivity audiohash 49f69a52extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

18 properties · 3 required · 0 $defs
propertytypedescriptionconstraints
tags*stringComma-separated list of genre tags to control the style of the generated audio.
audio_url*stringURL of the audio file to be outpainted.
original_tags*stringOriginal tags of the audio file.
minimum_guidance_scalenumberMinimum guidance scale for the generation after the decay.0 ≤ n ≤ 200 · default: 3
guidance_intervalnumberGuidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps)0 ≤ n ≤ 1 · default: 0.5
tag_guidance_scalenumberTag guidance scale for the generation.0 ≤ n ≤ 10 · default: 5
guidance_scalenumberGuidance scale for the generation.0 ≤ n ≤ 200 · default: 15
guidance_typeenumType of CFG to use for the generation process.cfg | apg | cfg_star · default: "apg"
schedulerenumScheduler to use for the generation process.euler | heun · default: "euler"
number_of_stepsintegerNumber of steps to generate the audio.3 ≤ n ≤ 60 · default: 27
granularity_scaleintegerGranularity scale for the generation process. Higher values can reduce artifacts.-100 ≤ n ≤ 100 · default: 10
original_lyricsstringOriginal lyrics of the audio file.default: ""
lyricsstringLyrics to be sung in the audio. If not provided or if [inst] or [instrumental] is the content of this field, no lyrics will be sung. Use control structures like [verse], [chorus] and [bridge] to control the structure of the song.default: ""
edit_modeenumWhether to edit the lyrics only or remix the audio.lyrics | remix · default: "remix"
seedintegerRandom seed for reproducibility. If not provided, a random seed will be used.nullable
lyric_guidance_scalenumberLyric guidance scale for the generation.0 ≤ n ≤ 10 · default: 1.5
guidance_interval_decaynumberGuidance interval decay for the generation. Guidance scale will decay from guidance_scale to min_guidance_scale in the interval. 0.0 means no decay.0 ≤ n ≤ 1 · default: 0
original_seedintegerOriginal seed of the audio file.nullable

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/ace-step/audio-to-audio","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}