wan/2-2-a14b-speech-to-video-turbo

📝 Model description pending (TODO). Every value on this page comes from the ModelFold catalog, and no technical detail has been invented.

Overview

Field	Value
Model ID	wan/2-2-a14b-speech-to-video-turbo
Family slug	wan-speech-to-video-turbo
Modality	Audio & Speech (audio)
Credits	10
Upstream cost	—
Pricing source	default — Not covered by upstream pricing table — modality default, pending manual review
Endpoint	POST /v1/audio/generations

Request example

export API_BASE="https://modelfold.ai/v1"
export MODELFOLD_API_KEY="mf-..."   # 在控制台 API Key 页面创建

curl -X POST "$API_BASE/audio/generations" \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"wan/2-2-a14b-speech-to-video-turbo","prompt":"The lady is talking","image_url":"https://file.aiquickdraw.com/custom-page/akr/section-images/1756797663082u4pjmcrq.png","audio_url":"https://file.aiquickdraw.com/custom-page/akr/section-images/17567977044127d1emlmc.mp3","num_frames":80,"frames_per_second":16,"resolution":"480p","num_inference_steps":27,"guidance_scale":3.5,"shift":5}'

Required parameters

Required: prompt, image_url, audio_url.

Pass model parameters at the top level; do not wrap them in input. Replace sample media URLs with your own publicly accessible files. The request waits for generation and returns data[].url.

See the complete parameter reference for conditional requirements, limits and alternative input modes.

Related models

• Model overview
• See all 10 audio & speech models
• elevenlabs/text-to-dialogue-v3
• elevenlabs/text-to-speech-multilingual-v2
• elevenlabs/text-to-speech-turbo-2-5
• gemini-omni-audio
• google/gemini-2-5-pro-tts
• google/gemini-3-1-flash-tts

See also

• API reference