GET

/v1/schemas/fal/video/fal-ai%2Fai-avatar%2Fmulti-text

kind inputactivity videohash 6baedfd0extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

10 properties · 4 required · 0 $defs
propertytypedescriptionconstraints
first_text_input*stringThe text input to guide video generation.
image_url*stringURL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.
prompt*stringThe text prompt to guide video generation.
second_text_input*stringThe text input to guide video generation.
voice1enumThe first person's voice to use for speech generationAria | Roger | Sarah | Laura | Charlie | George · +14 more · default: "Sarah"
voice2enumThe second person's voice to use for speech generationAria | Roger | Sarah | Laura | Charlie | George · +14 more · default: "Roger"
num_framesintegerNumber of frames to generate. Must be between 81 to 129 (inclusive). If the number of frames is greater than 81, the video will be generated with 1.25x more billing units.41 ≤ n ≤ 241 · default: 191
seedintegerRandom seed for reproducibility. If None, a random seed is chosen.0 ≤ n ≤ 4294967295 · default: 81
resolutionenumResolution of the video to generate. Must be either 480p or 720p.480p | 720p · default: "480p"
accelerationenumThe acceleration level to use for generation.none | regular | high · default: "regular"

Validate a payload

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