Digital Human Video
Model ID
Put this value in the request body's `model` field — not the display name above.
by other · Digital-human video: pick a digital-human avatar and a driving audio clip (or text) to get a talking avatar video (asynchronous task). Billed by video length.
Quick start
POST /v1/videos/generationshttps://qd.zsopc.com/v1curl https://qd.zsopc.com/v1/videos/generations \
-H "Authorization: Bearer sk-gpushare-xxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
"model": "dh-avatar",
"avatar": "<POST /v1/videos/avatars 拿到的形象 id>",
"audio_url": "https://example.com/voice.mp3",
"duration": 32
}'
# 返回 {"id": "...", "status": "queued"}
# duration 必填(秒):预留费用的依据,缺省直接 400
# 也可以用「文字 + 音色」驱动,不必先合成音频:
# {"model":"dh-avatar","avatar":"…","voice":"<音色 id>","text":"大家好…","duration":30}
# 中文口播时长约 = 字数 ÷ 3.3
# ⚠️ 外部 key 的预扣取「300 秒地板」与你传的 duration 的较大者curl https://qd.zsopc.com/v1/videos/generations/$TASK_ID \
-H "Authorization: Bearer sk-gpushare-xxxxxxxx"
# status: queued -> running -> succeeded / failed / expired / cancelled
# 建议 5-10 秒轮询一次。轮询免费。This is an async task: submit for a task ID, then poll until it settles. Polling itself is free.
Pricing
Billed per second of delivered video; tiered SKUs use the rate for the resolution actually delivered.
- Rates
- per second 3.962Credits
- Settlement
- Hold on submit (the greater of the 300-second floor and your `duration`) → settle on measured length → refund the difference
- This SKU's output length is set by the source media. On submit we hold the greater of a 300-second floor and the `duration` you pass, then settle on the measured length and refund the excess.
- So make sure your balance covers that hold (at least 300 seconds' worth) before submitting, or you get a straight 402.
- `duration` is required — pass the actual length in seconds of the driving audio or script; omitting it returns 400.
- Failed or expired tasks are refunded in full.
- Polling task status is free and does not count toward usage.
- All your API keys share one balance; when it runs out the API returns HTTP 402 `quota_exceeded`.
Sign in and any personal discount on your account will show up here. Sign in
Capabilities & specs
- Category
- Video generation
- Endpoint family
- Video generation (Videos)
- Released
- 2026-07-24
- License
- Closed source
Try it
Models like this bill for real per image / per second / per call and are mostly async tasks, so there is no one-click test here. Use the sample code above, or generate in the matching workbench (which has a parameter panel and a cost estimate).
Open the workbenchCommon errors
404 model_not_foundYou passed the display name instead of the model ID.✗ Digital Human Video→✓ dh-avatar
→ Copy the Model ID at the top of this page
402 quota_exceededInsufficient account balance. All your API keys share one balance.
401 / 403The API key is invalid, or it has a model allowlist that doesn't include this ID.
→ Check the key's status and allowed models
400 invalid_request`resolution` is required on Lite (`-lite`) SKUs and only accepts 720p / 1080p; anything else also returns 400.
→ Check your request body against the sample code above