2-2-a14b-speech-to-video-turbo
Wan 2.2 A14B is Wan's speech to video model, available here through a single relay API. It drives a talking-avatar video from audio or a script. Provide a source video plus a prompt describing the change. Requests run server-side against 97AI.PRO with your credit balance, so you get Wan quality without managing a separate Wan account or key.
Text prompt for video generation (max 5000 chars)
Input image URL; resized/center-cropped if needed (max 10MB)
Audio file URL for speech sync (max 10MB)
Frame count to generate; 40-120, multiple of 4
Video FPS (4-60)
Output video resolution
Negative prompt to exclude content (max 500 chars)
Random seed for reproducible results
Sampling steps for quality/speed tradeoff (2-40)
Prompt adherence strength; 1-10 scale
Video shift parameter (1.0-10.0)
Enable/disable content filtering