Wan Speech to video | PineRouter Docs

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

Use with POST /v1/jobs.

Price

Settings	Price
480p	$0.075 per second
580p	$0.112 per second
720p	$0.150 per second

Input fields

Field	Type or options	Default
`prompt`	string
`image_url`	string
`audio_url`	string
`num_frames`	number	`80`
`frames_per_second`	number	`16`
`resolution`	`480p` `580p` `720p`	`"480p"`
`negative_prompt`	string
`seed`	integer
`num_inference_steps`	number	`27`
`guidance_scale`	number	`3.5`
`shift`	number	`5`

Files are public https links. Safety filters are always on.

Example

curl https://pinerouter.ai/v1/jobs \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"wan/2-2-a14b-speech-to-video-turbo","input":{"num_frames":80,"frames_per_second":16,"resolution":"480p","num_inference_steps":27,"guidance_scale":3.5,"shift":5,"prompt":"Describe what you want"}}'

Then poll GET /v1/jobs/<id> until data.status is succeeded (links in data.outputs), or pass webhook_url to be called when it finishes; see Jobs.

import time, requests

BASE, H = "https://pinerouter.ai", {"Authorization": "Bearer YOUR_API_KEY"}
job = requests.post(f"{BASE}/v1/jobs", headers=H, json={"model":"wan/2-2-a14b-speech-to-video-turbo","input":{"num_frames":80,"frames_per_second":16,"resolution":"480p","num_inference_steps":27,"guidance_scale":3.5,"shift":5,"prompt":"Describe what you want"}}).json()["data"]
while job["status"] not in ("succeeded", "failed"):
    time.sleep(5)
    job = requests.get(f"{BASE}/v1/jobs/{job['id']}", headers=H).json()["data"]
print(job["outputs"] or job.get("error"))