Emo.
设备端表情符号建议：输入一条任务或消息，返回贴合的表情符号，支持 22 种语言。
演示
比你打字还快。
「看牙医」返回 🦷 🪥 🏥 🩺，「付账单」返回 💰 💳 🧾。Emo 是按人们在待办清单和聊天里写东西的方式调优的，而不是按写文章的方式，每条建议都附带肤色变体。
表情选择器摆出一个网格，让人自己翻找。Emo 读取文本，直接给出贴合的表情符号，就像输入法给出下一个词一样。Emo 足够小、足够快，可以在每一次按键时运行，而且从不调用服务器。
建议用时不到 2 毫秒。
5 MB 的 Core ML 模型，2 毫秒内给出建议，覆盖 22 种语言。
内部测量数据。表情符号的语义是近似的，因此排名靠前处出现接近的并列属于预期。
在用户打字时就给出建议
字还没打完，候选栏里就已经摆好了表情符号，就像输入法联想词语一样。全部在设备上完成，没有网络往返。
事件一创建就打上标签
针对短条目调优：「看牙医」返回 🦷 🪥 🏥 🩺，日历或任务应用因此可以在用户按下保存的那一刻就给这一条加上标签。
给草稿消息配表情
消息还在写的时候就给出贴合的表情符号，支持 22 种语言中的任意一种，草稿不会被发往任何地方。
保留选择器，再加上建议
Emo 负责填满键盘上方的候选条，知道自己想要什么的用户照样翻网格，其他人则第一眼就看到对的表情符号。
灵感
用 Emo 构建的点子。把提示词复制到你的编码 agent 里就能开始。
Add an emoji suggestion strip above the keyboard.
Add a suggestion strip that calls Desert Ant's Emo on-device as the user types and offers the emoji that fit the sentence, in their language, with no network call. Build it with the Desert Ant SDK. Emo (Swift, Kotlin, JavaScript / TypeScript). Install and API: https://desertant.com/docs/emo/. Install: SwiftPM desert-ant-core; Maven ai.desertant:emo:3.1.0; npm i @desert-ant-labs/emo @litertjs/core. SDK source: https://github.com/Desert-Ant-Labs/desert-ant-core. Machine-readable catalog of every model and SDK: https://desertant.com/llms.txt.
Suggest a reaction emoji for any message.
In a chat app, use Desert Ant's Emo on-device to suggest a fitting reaction emoji for the message a user is looking at, faster than they could scroll a picker. Build it with the Desert Ant SDK. Emo (Swift, Kotlin, JavaScript / TypeScript). Install and API: https://desertant.com/docs/emo/. Install: SwiftPM desert-ant-core; Maven ai.desertant:emo:3.1.0; npm i @desert-ant-labs/emo @litertjs/core. SDK source: https://github.com/Desert-Ant-Labs/desert-ant-core. Machine-readable catalog of every model and SDK: https://desertant.com/llms.txt.
Tag a post and suggest an emoji for it.
As a user drafts a post, run Desert Ant's Gist to tag its topic and Emo to suggest a fitting emoji, both on-device. Build it with the Desert Ant SDK. Gist (Swift, Kotlin, JavaScript / TypeScript). Install and API: https://desertant.com/docs/gist/. Emo (Swift, Kotlin, JavaScript / TypeScript). Install and API: https://desertant.com/docs/emo/. SDK source: https://github.com/Desert-Ant-Labs/desert-ant-core. Machine-readable catalog of every model and SDK: https://desertant.com/llms.txt.
Auto-add an emoji to a task or calendar title.
Use Desert Ant's Emo on-device to add a fitting emoji to a task or event title as it's created, in the user's language. Build it with the Desert Ant SDK. Emo (Swift, Kotlin, JavaScript / TypeScript). Install and API: https://desertant.com/docs/emo/. Install: SwiftPM desert-ant-core; Maven ai.desertant:emo:3.1.0; npm i @desert-ant-labs/emo @litertjs/core. SDK source: https://github.com/Desert-Ant-Labs/desert-ant-core. Machine-readable catalog of every model and SDK: https://desertant.com/llms.txt.
Build an emoji search that understands a sentence, not just keywords.
Build an emoji picker that runs Desert Ant's Emo on-device so typing a phrase surfaces the emoji that fit the meaning, faster than scrolling. Build it with the Desert Ant SDK. Emo (Swift, Kotlin, JavaScript / TypeScript). Install and API: https://desertant.com/docs/emo/. Install: SwiftPM desert-ant-core; Maven ai.desertant:emo:3.1.0; npm i @desert-ant-labs/emo @litertjs/core. SDK source: https://github.com/Desert-Ant-Labs/desert-ant-core. Machine-readable catalog of every model and SDK: https://desertant.com/llms.txt.
Suggest a status emoji from what someone is typing.
In a chat or status field, run Desert Ant's Emo on-device to suggest a status emoji from the text the user is writing. Build it with the Desert Ant SDK. Emo (Swift, Kotlin, JavaScript / TypeScript). Install and API: https://desertant.com/docs/emo/. Install: SwiftPM desert-ant-core; Maven ai.desertant:emo:3.1.0; npm i @desert-ant-labs/emo @litertjs/core. SDK source: https://github.com/Desert-Ant-Labs/desert-ant-core. Machine-readable catalog of every model and SDK: https://desertant.com/llms.txt.
模型能做什么
- 精选 812 个日常表情符号词表，含肤色变体。
- 多语言：22 种语言，包括中日韩、阿拉伯语、泰语和印地语。
- 设备端每条建议用时远低于 2 毫秒。
- Apple 上 5 MB，LiteRT 上 11 MB。不调用服务器。
快速上手
只需几行代码，即可为你的 iOS or macOS, Android or web 应用加上 表情符号建议。 Emo 文档.
// Swift Package Manager
.package(url: "https://github.com/Desert-Ant-Labs/desert-ant-core", from: "3.1.0")
// target dependency
.product(name: "Emo", package: "desert-ant-core")import Emo
let emo = Emo()
let suggestions = try await emo.suggestions(for: "Pay my bills")
// [EmoSuggestion(emoji: "💰", confidence: ...), ...]Add Emo from Desert Ant Labs to this Swift project (iOS, macOS). What it does: Emo：设备端表情符号建议. SDK: Swift (iOS, macOS) Repo: https://github.com/Desert-Ant-Labs/desert-ant-core#readme // Swift Package Manager .package(url: "https://github.com/Desert-Ant-Labs/desert-ant-core", from: "3.1.0") // target dependency .product(name: "Emo", package: "desert-ant-core") Reference: - Model page: https://desertant.com/models/emo/ - Full catalog and other models: https://desertant.com/llms.txt Add the SDK, then follow its README for the exact API and current version. Do not invent API names or method signatures; confirm them against the README.
// build.gradle.kts (Maven Central)
implementation("ai.desertant:emo:3.1.0")import ai.desertant.emo.Emo
Emo(context).use { emo ->
val suggestions = emo.suggestions("Pay my bills")
// List<EmoSuggestion>
}Add Emo from Desert Ant Labs to this Kotlin project (Android).
What it does: Emo：设备端表情符号建议.
SDK:
Kotlin (Android)
Repo: https://github.com/Desert-Ant-Labs/desert-ant-core#readme
// build.gradle.kts (Maven Central)
implementation("ai.desertant:emo:3.1.0")
Reference:
- Model page: https://desertant.com/models/emo/
- Full catalog and other models: https://desertant.com/llms.txt
Add the SDK, then follow its README for the exact API and current version. Do not invent API names or method signatures; confirm them against the README.
npm i @desert-ant-labs/emo @litertjs/coreimport { Emo } from "@desert-ant-labs/emo";
const emo = await Emo.load();
const results = await emo.suggestions("Pay my bills");
// [{ emoji: "💰", confidence: 0.62 }, ...]Add Emo from Desert Ant Labs to this JavaScript / TypeScript project (Web, Node.js). What it does: Emo：设备端表情符号建议. SDK: JavaScript / TypeScript (Web, Node.js) Repo: https://github.com/Desert-Ant-Labs/desert-ant-core#readme npm i @desert-ant-labs/emo @litertjs/core Reference: - Model page: https://desertant.com/models/emo/ - Full catalog and other models: https://desertant.com/llms.txt Add the SDK, then follow its README for the exact API and current version. Do not invent API names or method signatures; confirm them against the README.
规格
- 语言
- 22 种，包括英语、西班牙语、法语、德语、葡萄牙语和日语
- 设备端体积
- Apple 上通过 Core ML 为 5 MB，其他平台通过 LiteRT 为 11 MB（模型 + 分词器）
- 速度
- 每条建议用时不到 2 毫秒
- 模型
- 双流文本分类器：词汇 n-gram 加多语言嵌入
Emo 针对任务、条目、消息这类带有明确意图的短文本调优。长篇文本给出的建议会更杂。表情符号的含义本身就不精确，因此排名靠前的几个结果常常难分高下；语料较少的那几种语言，表现也会比英语稍弱。
常见问题
Emo 是什么？
设备端表情符号建议：输入一条任务或消息，返回贴合的表情符号，支持 22 种语言。
Emo 在设备上运行吗？
是的。Emo 在设备上运行，不调用任何服务器，因此数据始终留在用户手中。
Emo 支持哪些平台？
Emo 以面向 Swift, Kotlin, JavaScript / TypeScript 的原生设备端 SDK 形式提供。
Emo 的价格是多少？
每个模型的每个 SDK 均可免费支持最多 10 万台月活跃设备。每位用户调用模型的次数不设上限。 如需定制授权，请联系我们。
Emo 的准确度和速度如何？
5 MB 的 Core ML 模型，2 毫秒内给出建议，覆盖 22 种语言。