模型市场支持← 返回应用

Gemini Omni

Gemini Omni 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 3 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
Gemini Omni VideoText to Videogemini-omni-video
Gemini Omni AudioText to Speechgemini-omni-audio
Gemini Omni CharacterChatgemini-omni-character

Gemini Omni Video · Text to Video

POSTText to Videogemini-omni-video
input 字段
promptstring必填

Video prompt describing content, style, camera language, or actions

image_urlsarray<string>可选

Array of reference image URLs (max 7, each <=20MB)

audio_idsarray<string>可选

Audio IDs from gemini-omni-audio for narration/dialogue (max 3)

video_listarray<object>可选

Source video clips with trim ranges (max 1, <=100MB, <=30s)

character_idsarray<string>可选

Character IDs from gemini-omni-character API (max 3)

durationenum<string>可选

Generated video duration in seconds

aspect_ratioenum<string>可选

Video aspect ratio (16:9 landscape, 9:16 portrait)

seedinteger可选

Random seed [0, 2147483647] for reproducibility

resolutionenum<string>可选

Output video resolution

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gemini-omni-video",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "image_urls": [
      "https://example.com/input.jpg"
    ],
    "audio_ids": [
      "https://example.com/reference.mp3"
    ],
    "video_list": [],
    "character_ids": [
      "https://example.com/file"
    ],
    "duration": "4",
    "aspect_ratio": "16:9",
    "seed": 42,
    "resolution": "720p"
  }
}'

Gemini Omni Audio · Text to Speech

POSTText to Speechgemini-omni-audio
input 字段
audio_idenum<string>必填

Voice character preset selection

namestring必填

Voice identifier (max 210 characters)

voice_descriptionstring可选

Timbre, style, rate, emotion characteristics (max 20000 chars)

example_dialoguestring可选

Sample speech utterance for voice preview (max 120 chars)

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gemini-omni-audio",
  "input": {
    "audio_id": "achernar",
    "name": "example",
    "voice_description": "example",
    "example_dialogue": "example"
  }
}'

Gemini Omni Character · Chat

POSTChatgemini-omni-character
input 字段
descriptionsstring必填

Character appearance, identity, style, clothing, or personality

image_urlsarray<string>必填

Array of character reference image URLs (max 1, <=20MB each)

audio_idsarray<string>可选

Audio IDs from gemini-omni-audio for voice traits/persona

character_namestring可选

Character name

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gemini-omni-character",
  "input": {
    "descriptions": "example",
    "image_urls": [
      "https://example.com/input.jpg"
    ],
    "audio_ids": [
      "https://example.com/reference.mp3"
    ],
    "character_name": "example"
  }
}'