Try Wan 2.7 text-to-video online, review a cinematic preview, compare 720P and 1080P per-second pricing, and integrate POST /v1/tasks.
Provider: Alibaba
Category: video generation
Endpoint: /v1/tasks
Status: Available
Cost: See live page pricing
Alibaba Tongyi Wanxiang 2.7 text-to-video model: 1080P, native audio, up to 15 seconds.
Pricing
Standard Usage
Choose 2-15 seconds in 1-second steps
Upload an audio file. Supports MP3/WAV/WebM/M4A/AAC/OGG, max 15MB
Describe what should not appear in the result; Up to 500 characters
Automatically improve the prompt for more complete generation
Whether to add an AI-generated watermark
Ready for generation
Configure your parameters and click "Run" to see the output here.
Public model preview
This model preview demonstrates a cinematic café scene with visible subject motion, rain, and shallow depth of field. Copy the complete prompt to adapt it.
A warm interior, restrained character motion, rain on glass, and shallow depth of field create a compact cinematic scene.
Prompt shown with this public preview
一位穿着白色毛衣的年轻女子坐在咖啡馆窗边，窗外是雨天的街道，她轻轻端起咖啡杯，目光望向窗外，暖黄色灯光映照在她的脸上，雨滴顺着玻璃缓缓流下，电影级浅景深，35mm胶片质感，温暖色调，慢镜头特写
Choose by input method, output specifications, control surface, and budget.
Long-form text-to-video
Compare up to 30 seconds, seven aspect ratios, and synchronized audio generation.
Wan 2.7 creates 2–15 second videos at 720P or 1080P in five aspect ratios. It supports prompt extension, negative prompts, seeds, and an optional audio reference URL.
The route remains text-to-video: audio is optional guidance, not an image input. Use the separate image-to-video model for first or last frames. wan2.7-video/text-to-video
These specifications reflect the current HiAPI Wan 2.7 Text to Video request contract.
Validate the shot at 720P, then move to 1080P; add audio only when timing or sound guidance is required.
This is the minimum request for an asynchronous text-to-video task. Use the API docs for task retrieval, callbacks, errors, and the complete parameter contract.
curl -X POST "https://api.hiapi.ai/v1/tasks" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan2.7-video/text-to-video",
"input": {
"prompt": "A calm sunrise over a quiet lake, cinematic, slow camera movement",
"resolution": "720P",
"ratio": "16:9",
"duration": 5,
"prompt_extend": true,
"watermark": false
}
}'No. wan2.7-video/text-to-video requires a prompt only. Use Wan 2.7 Image-to-Video for first or last frames.
It supports 2–15 seconds at 720P or 1080P in 16:9, 9:16, 1:1, 4:3, or 3:4.
audio_url is an optional WAV or MP3 reference. It does not turn this route into image-to-video or replace the text prompt.
It is billed per output second with separate 720P and 1080P rates.
POST an asynchronous task to /v1/tasks with model set to wan2.7-video/text-to-video and pass prompt, resolution, ratio, and duration inside input.
Lead with subject and setting, then describe action, camera direction, and speed in time order. State no cuts for a continuous take.
Draft
5s · 720P
Final
2–15s · 1080P
Validate subject motion and camera continuity with 5s · 720P, then move to 2–15s · 1080P.
Check motion stability and subject consistency online, then create an asynchronous task with the same model ID: wan2.7-video/text-to-video.