Spiral gives your agent every tool with one account. Browse the tools →

falVideoAvailable nowReleased 2025-08-26

Wan-2.2 14B · Speech to Video

fal-ai/wan/v2.2-14b/speech-to-video

Make a talking video from a photo and audio with Wan-2.2 14B · Speech to Video from fal through one Spiral API key. It runs in the background and returns video. Pay as you go, with no subscription.

Pricing

resolution: 480p (default) $0.13, 580p $0.195, 720p $0.26 per second.

Limits

Runs
In the background
Returns
video
Longest queue wait
1 hour
Run deadline
30 minutes
Longest run, end to end
930 minutes
Largest inline input
1 MB
Largest input file
2 GB
Largest output
5 GB

Input

FieldKindDefaultDescription
prompt requiredtext—

The text prompt used for video generation.

negative_prompttext

Negative prompt for video generation.

num_framesnumber (whole)
40 to 120
80

Number of frames to generate. Must be between 40 to 120, (must be multiple of 4).

frames_per_secondnumber (whole)
4 to 60
16

Frames per second of the generated video. Must be between 4 to 60. When using interpolation and adjust_fps_for_interpolation is set to true (default true,) the final FPS will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If adjust_fps_for_interpolation is set to false, this value will be used as-is.

seednumber (whole)—

Random seed for reproducibility. If None, a random seed is chosen.

resolutionone of
480p, 580p, 720p
480p

Resolution of the generated video (480p, 580p, or 720p).

num_inference_stepsnumber (whole)
2 to 40
27

Number of inference steps for sampling. Higher values give better quality but take longer.

guidance_scalenumber
1 to 10
3.5

Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.

shiftnumber
1 to 10
5

Shift value for the video. Must be between 1.0 and 10.0.

video_qualityone of
low, medium, high, maximum
high

The quality of the output video. Higher quality means better visual quality but larger file size.

video_write_modeone of
fast, balanced, small
balanced

The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size.

image_url requiredURL or file—

URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.

audio_url requiredURL or file—

The URL of the audio file.

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/wan/v2.2-14b/speech-to-video",
    "input": {
      "prompt": "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard.",
      "image_url": "https://storage.googleapis.com/falserverless/example_inputs/wan_s2v_cat.png",
      "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/wan_s2v_talk.wav"
    }
  }'

Frequently asked questions

How much does Wan-2.2 14B · Speech to Video cost?

`resolution`: 480p (default) $0.13, 580p $0.195, 720p $0.26 per second. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

How do I use Wan-2.2 14B · Speech to Video through an API?

Send `POST /v1/runs` with `"provider": "fal"`, `"model": "fal-ai/wan/v2.2-14b/speech-to-video"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.

Do I need an account with fal to use Wan-2.2 14B · Speech to Video?

No. Spiral runs it on its own fal account and charges your Spiral balance.

Can my AI agent use Wan-2.2 14B · Speech to Video?

Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.