lala Models API — 开发者文档

认证

所有请求带 header x-lala-key: <你的 API key>（或标准 Authorization: Bearer <key>）。

申请 key：邮件 [email protected]或经 WhatsApp 联络我们。

模型列表

curl https://lala.buddylala.ai/v1/models -H "x-lala-key: $LALA_KEY"

对话 Chat Completions

OpenAI-compatible。支持 stream: true 串流输出。

curl

curl https://lala.buddylala.ai/v1/chat/completions \
  -H "x-lala-key: $LALA_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "lala-6",
    "messages": [{"role": "user", "content": "你好，介绍下自己"}],
    "max_tokens": 500
  }'

Python（openai SDK）

from openai import OpenAI

client = OpenAI(
    base_url="https://lala.buddylala.ai/v1",
    api_key="***",   # 你的 lala key
)

resp = client.chat.completions.create(
    model="lala-super",
    messages=[{"role": "user", "content": "写一首关于秋天的诗"}],
)
print(resp.choices[0].message.content)

Node.js

const res = await fetch("https://lala.buddylala.ai/v1/chat/completions", {
  method: "POST",
  headers: {
    "x-lala-key": process.env.LALA_KEY,
    "content-type": "application/json",
  },
  body: JSON.stringify({
    model: "lala-ultrafast",
    messages: [{ role: "user", content: "1+1=?" }],
    stream: false,
  }),
});
const data = await res.json();
console.log(data.choices[0].message.content);

向量 Embeddings

curl https://lala.buddylala.ai/v1/embeddings \
  -H "x-lala-key: $LALA_KEY" -H "Content-Type: application/json" \
  -d '{"model": "lala-rag", "input": "宠物食品零售自动化"}'

回传标准 OpenAI embeddings 格式（data[].embedding 向量阵列），可直接入向量数据库做 RAG。

图像生成 Image

curl https://lala.buddylala.ai/v1/images/generations \
  -H "x-lala-key: $LALA_KEY" -H "Content-Type: application/json" \
  -d '{"model": "lala-image", "prompt": "a cute corgi puppy, studio photo", "n": 1}'

回传 data[].url（图片 CDN 链接）。计费：每张固定价，见价格页。

视频生成 Video（任务式）

视频生成是两段式：先提交任务取得 task id，再轮询取得结果。

步骤 1：提交任务

curl https://lala.buddylala.ai/v1/responses \
  -H "x-lala-key: $LALA_KEY" -H "Content-Type: application/json" \
  -d '{
    "model": "lala-video",
    "input": [{"type": "text", "text": "a cat yawning in sunlight"}],
    "duration": 5,
    "resolution": "720p",
    "ratio": "16:9",
    "generate_audio": true
  }'
# → {"id": "cgt-xxxx", ...}   ← 保存此任务识别码！

参数：duration 4–30 秒（或 -1 智能选择）、resolution 480p/720p/1080p、ratio 16:9 / 4:3 / 1:1 / 3:4 / 9:16 / 21:9 / adaptive、generate_audio 默认 true（自动配人声／音效／背景乐）。

步骤 2：轮询结果

curl https://lala.buddylala.ai/v1/responses \
  -H "x-lala-key: $LALA_KEY" -H "Content-Type: application/json" \
  -d '{"model": "lala-video-get", "input": "cgt-xxxx"}'
# status: succeeded 时 output[].content[].text = 视频下载 URL

语音合成 Speech (TTS)

curl https://lala.buddylala.ai/v1/responses \
  -H "x-lala-key: $LALA_KEY" -H "Content-Type: application/json" \
  -d '{
    "model": "lala-speech",
    "input": "你好，欢迎致电 Buddylala",
    "output_format": "hex",
    "voice_setting": {"voice_id": "male-qn-qingse", "speed": 1, "vol": 1, "pitch": 0}
  }'
# → {"data": {"audio": "<hex 编码音频>"}}

hex 转 mp3：python3 -c "import binascii,sys; open('out.mp3','wb').write(binascii.unhexlify(sys.argv[1]))" "<hex>"。80+ 预置音色、9 种情绪。

音乐生成 Music

curl https://lala.buddylala.ai/v1/responses \
  -H "x-lala-key: $LALA_KEY" -H "Content-Type: application/json" \
  -d '{
    "model": "lala-music",
    "input": "upbeat jingle for a pet shop",
    "lyrics": "la la la happy day with you"
  }'
# → {"data": {"audio": "<hex>"}}

lyrics 必填（可先用 lala-lyric 生成）。

歌词生成 Lyric

curl https://lala.buddylala.ai/v1/responses \
  -H "x-lala-key: $LALA_KEY" -H "Content-Type: application/json" \
  -d '{
    "model": "lala-lyric",
    "mode": "write_full_song",
    "input": "一首关于猫的轻快广东歌"
  }'
# → {"song_title": "...", "style_tags": "...", "lyrics": "[Verse]..."}

mode：write_full_song（完整歌曲）或 edit（续写／修改，需带 lyrics 现有内容）。

结构化判研 Decision（非文本生成）

lala-decision不生成文本，只做结构化判断：提供一段状态（工单／对话／日志）＋一组问题，并行回传 Choice / Score / Noul 三类答案附校准概率。支持图像判断：可附最多 4 张图（PNG/JPEG/WebP，每张 ≤4MiB，base64 内嵌，不收 remote URL）一并分析。典型回应 1–5 秒，适合工单分派、意图识别、内容风控。

curl https://lala.buddylala.ai/typesafe/systemone \
  -H "x-lala-key: $LALA_KEY" -H "Content-Type: application/json" \
  -d '{
    "model": "lala-decision",
    "state": "Customer: my order is 5 days late and I want a refund!",
    "questions": {
      "urgency": {
        "type": "choice",
        "instructions": "判断工单紧急程度",
        "criteria": {"低": "语气平和", "中": "有不满但无期限", "高": "情绪激动或提退款"}
      },
      "refund_requested": {
        "type": "noul",
        "instructions": "客户是否明确要求退款？"
      }
    }
  }'
# → {"answers": {"refund_requested": {"noul": 0.99, "type": "noul"}}, "model": "lala-decision", ...}

问题类型：choice（criteria 系 object：选项名→判定标准）、score（criteria 系 array：由低到高档位）、noul（true/false 判断，不需 criteria）。

图像判断（可选）：在 body 加"images": ["<base64 图片>"]（最多 4 张；每张 ≤4MiB、16 megapixels；整个 request body ≤13MiB；只收 base64 内嵌，不收 URL）。示例：

{
  "model": "lala-decision",
  "images": ["iVBORw0KGgo...（base64 PNG）"],
  "state": "客人传送了一张收据照片，要求我们查看",
  "questions": {
    "is_valid_receipt": {"type": "noul", "instructions": "图片是否为一张有效收据？"}
  }
}

错误处理

Response 文字经 brand normalization（供应商相关字样会统一为 lala/buddylala 品牌称呼），JSON 结构及字段完全标准，不影响解析。