PopNowAPI 文档
正文

Talking Avatar API 调用参考

一张人像加一段配音,生成口型同步的说话视频

用一个 PopNow API 密钥,就能在自己的代码里调用 Talking Avatar。下面列出要填的调用名、这个型号接受的每个输入字段、每次请求花多少积分,以及一段可以直接粘进终端运行的请求。

参数说明直接取自型号的输入 schema,暂时只有英文。

一览

出品方
PopNow
产出
视频
起价
2.7 积分 每秒成片 ($0.027)

1 积分 = 0.01 美元。任务受理时先冻结可能的最高费用,完成后按实际用量结算、向上取整到整积分,多冻的退回;失败的任务不扣积分。想在运行前知道确切数字,先调 POST /api/v1/jobs/quote。

数字人

popnow/talking-avatar-v1/talking-avatar

价格

选项积分 (每秒成片)美元
默认2.7$0.027

参数

字段类型默认值取值范围作用
image_url必填string——Portrait of the person who will speak. One clearly visible face, looking roughly at the camera, works best.
audio_url必填string——Speech that drives the lips, 3 to 60 seconds, MP3 or WAV. The video runs as long as this audio; files outside that range are rejected before any charge.
prompt可选string—最多 1000 个字符Optional note on expression or mood, such as calm or cheerful. Identity and setting come from the portrait.
mask_url可选string——Optional black-and-white mask the same size as the portrait, white over the person who should speak. Only needed when the portrait shows several people.
seed可选integer—0 到 2147483647Random seed for controlled comparisons.

请求示例

这段请求原样就能运行,没写的字段都用默认值。运行前先把密钥放进环境变量 POPNOW_API_KEY。

示例里的 audio_url, image_url 用的是 PopNow 的示例素材,换成你自己的公开 HTTPS 链接、上传文件或已保存的素材即可。

POST /api/v1/jobs/createTask
curl -X POST "https://api.popnow.ai/api/v1/jobs/createTask" \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "popnow/talking-avatar-v1/talking-avatar",
  "input": {
    "prompt": "Speaks warmly to the camera with natural head movement and a relaxed smile",
    "image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
    "audio_url": "https://media.popnow.ai/shortfilm/voices/Aoede-46e4c427.mp3"
  }
}'

响应里会立刻带回 taskId。之后用 GET /api/v1/jobs/recordInfo 取结果,或者在请求里加上 callBackUrl 等通知。

GET /api/v1/jobs/recordInfo
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

接下来

本页内容