Skip to content
Docs menu

Video models

Wan 2.2 A14B Speech to Video Turbo

On this page

Wan 2.2 A14B Speech to Video Turbo — high-quality AI video generation.

modelIdwan-2-2-a14b-speech-to-video-turbo
Modalityvideo
PricingSee this model on the Pricing page for the current per-call price (with your markup).

Operations

OperationmodelIdEndpointRequired input
Defaultwan-2-2-a14b-speech-to-video-turboPOST /api/v1/generateprompt, image_url, audio_url
Poll taskGET /api/v1/task/{id}?model=wan-2-2-a14b-speech-to-video-turbo

Input parameters

FieldTypeRequiredValues / example
promptstringYesThe text prompt used for video generation Max 5000 characters. (default: Subtle lifelike motion driven by the audio, gentle natural head movement, soft cinematic lighting, smooth realistic delivery.)
image_urlstringYesURL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped (image URL)
audio_urlstringYesThe URL of the audio file (image URL)
num_framesnumberNoNumber of frames to generate. Must be between 40 to 120, (must be multiple of 4) (range 40-120) (default: 80)
frames_per_secondnumberNoFrames 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 (range 4-60) (default: 16)
resolutionstringNoResolution of the generated video (480p, 580p, or 720p) (options: 480p | 580p | 720p) (default: 480p)
negative_promptstringNoNegative prompt for video generation Max 500 characters.
seednumberNoRandom seed for reproducibility. If None, a random seed is chosen
num_inference_stepsnumberNoNumber of inference steps for sampling. Higher values give better quality but take longer (range 2-40) (default: 27)
guidance_scalenumberNoClassifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality (range 1-10) (default: 3.5)
shiftnumberNoShift value for the video. Must be between 1.0 and 10.0 (range 1-10) (default: 5)
enable_safety_checkerbooleanNoIf set to true, input data will be checked for safety before processing (true/false) (default: true)
nsfw_checkerbooleanNoA configurable parameter. Defaults to true in the Playground. (true/false) (default: true)

Example request

bash
curl -X POST https://you.bot/api/v1/generate \
  -H "Authorization: Bearer $YOUBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"modelId":"wan-2-2-a14b-speech-to-video-turbo","input":{"prompt":"A cinematic aerial shot of a coastal town at golden hour, gentle waves rolling onto the shore, warm light, slow camera push-in.","image_url":"https://example.com/input.jpg","audio_url":"https://example.com/input.mp3","num_frames":80,"frames_per_second":16,"resolution":"480p","negative_prompt":"blurry, low quality, distorted, watermark, text","seed":1,"num_inference_steps":27,"guidance_scale":3.5,"shift":5,"enable_safety_checker":true,"nsfw_checker":true}}'