GET

/v1/schemas/fal/audio/fal-ai%2Fltx-2.3-quality%2Ftext-to-audio

kind inputactivity audiohash f3e0c1a1extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

10 properties · 1 required · 0 $defs
propertytypedescriptionconstraints
prompt*stringThe prompt to generate the audio from.
num_framesintegerThe audio duration expressed in LTX video-frame units. Duration is approximately num_frames / frames_per_second seconds.9 ≤ n ≤ 481 · default: 121
enable_prompt_expansionbooleanWhether to enable prompt expansion.default: false
frames_per_secondnumberFrame rate used to derive the generated audio duration.1 ≤ n ≤ 60 · default: 24
enable_safety_checkerbooleanWhether to enable the safety checker.default: true
negative_promptstringThe negative prompt to steer generation away from.default: "pc game, console game, video ga…
seedintegerRandom seed for reproducibility. If None, a random seed is chosen.nullable
sync_modebooleanIf True, the audio is returned as a data URI inline in the response. Useful for short-lived requests and tests.default: false
guidance_scalenumberClassifier-free guidance scale.1 ≤ n ≤ 20 · default: 1
num_inference_stepsintegerNumber of inference steps.8 ≤ n ≤ 30 · default: 15

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/ltx-2.3-quality/text-to-audio","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}