falVideo to videoComing soon
fal-ai/hunyuan-video-foley
fal-ai/hunyuan-video-foley is a video to video tool from fal that runs in the background and returns video. Coming soon: listed with its price, not yet open to runs.
This tool is listed but not yet available to run.
Priced by usagePricing
$0.13 per 10 seconds. Measured from the input file. The final charge comes from usage.
Limits
- Runs
- In the background
- Returns
- video
- Longest queue wait
- 3600s
- Run deadline
- 1800s
- Largest inline input
- 1024 KB
- Largest input file
- 500 MB
- Largest output
- 4768 MB
- Outputs per run
- 16
Input
| Field | Kind | Default | Description |
|---|---|---|---|
video_url required | URL or file | — | The URL of the video to generate audio for. |
text_prompt required | text | — | Text description of the desired audio (optional). |
negative_prompt | text | noisy, harsh | Negative prompt to avoid certain audio characteristics. |
guidance_scale | number 1 to 10 | 4.5 | Guidance scale for audio generation. |
num_inference_steps | number (whole) 10 to 100 | 50 | Number of inference steps for generation. |
seed | number (whole) | — | Random seed for reproducible generation. |
Same request in code
curl https://api.spiral.ai/v1/runs \
-H "Authorization: Bearer $SPIRAL_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"provider": "fal",
"model": "fal-ai/hunyuan-video-foley",
"input": {
"video_url": "https://storage.googleapis.com/falserverless/model_tests/video_models/1_video.mp4",
"text_prompt": "A person walks on frozen ice"
}
}'