模型市场支持← 返回应用

Volcengine

Volcengine 模型通过一个统一的异步任务 API 调用。用 POST /api/generate 发起任务，再轮询 GET /api/generate/{taskId} 直到完成。本系列提供 1 个端点。

概览

每个端点共享相同的外层结构 —— 只有 model 和 input 字段不同。可在模型市场的 playground 中运行任意一个。

认证

在 /api-keys 创建 API 密钥，然后作为 Bearer token 发送。已登录时从浏览器发起的请求也可通过会话 cookie 生效。

Authorization: Bearer <YOUR_API_KEY>

创建任务

POST
POST https://api.lithovas.com/api/generate

请求体：{ "model": "<slug>", "input": { … } }

响应：{ "taskId": "<id>", "state": "waiting" }

查询结果

GET
GET https://api.lithovas.com/api/generate/<taskId>

响应：{ "taskId", "state": "waiting" | "success" | "fail", "resultUrls": [ … ], "creditsConsumed", "failMsg", "balance" }

异步
创建任务返回 200 只表示任务已被接受 —— 并非已完成。请轮询此端点，直到 state 变为 success 或 fail。失败任务不计费。

端点

模型任务model slug
Video To Video Lip SyncVideo to Videovolcengine/video-to-video-lip-sync

Video To Video Lip Sync · Video to Video

POSTVideo to Videovolcengine/video-to-video-lip-sync
input 字段
modeenum<string>必填

Service mode: lite for frontal videos, basic for complex scenes

video_urlstring必填

Video URL (360p-1080p; MOV, MP4, HDR; max 500MB)

audio_urlstring必填

Target audio URL to drive lip movements; max 10MB

separate_vocalboolean可选

Enable vocal separation to suppress background noise

open_scenedetboolean可选

Enable scene segmentation and speaker ID (basic mode only)

align_audioboolean可选

Loop video when audio is longer than video (lite mode)

align_audio_reverseboolean可选

Loop video backward; requires align_audio=true (lite mode)

templ_start_secondsnumber可选

Start time of template video in seconds (lite mode)

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "volcengine/video-to-video-lip-sync",
  "input": {
    "mode": "lite",
    "video_url": "https://example.com/reference.mp4",
    "audio_url": "https://example.com/reference.mp3",
    "separate_vocal": false,
    "open_scenedet": false,
    "align_audio": true,
    "align_audio_reverse": false,
    "templ_start_seconds": 0
  }
}'