GET
/v1/schemas/fal/video/fal-ai%2Flongcat-single-avatar%2Faudio-to-video
Accept:
Request body
11 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| audio_url* | string | The URL of the audio file to drive the avatar. | |
| seed | integer | The seed for the random number generator. | nullable |
| enable_prompt_expansion | boolean | Whether to enable prompt expansion using an LLM to enhance the prompt for better video quality. | default: false |
| resolution | enum | Resolution of the generated video (480p or 720p). Billing is per video-second (16 frames): 480p is 1 unit per second and 720p is 4 units per second. | 480p | 720p · default: "480p" |
| negative_prompt | string | The negative prompt to avoid in the video generation. | default: "Close-up, Bright tones, overexp… |
| num_inference_steps | integer | The number of inference steps to use. | 10 ≤ n ≤ 100 · default: 50 |
| prompt | string | The prompt to guide the video generation. | default: "A person is talking naturally w… |
| audio_guidance_scale | number | The audio guidance scale. Higher values may lead to exaggerated mouth movements. | 1 ≤ n ≤ 10 · default: 4 |
| text_guidance_scale | number | The text guidance scale for classifier-free guidance. | 1 ≤ n ≤ 10 · default: 4 |
| enable_safety_checker | boolean | Whether to enable safety checker. | default: true |
| num_segments | integer | Number of video segments to generate. Each segment adds ~5 seconds of video. First segment is ~5.8s, additional segments are 5s each. | 1 ≤ n ≤ 10 · default: 1 |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/longcat-single-avatar/audio-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}