Title.
设备端标题与描述：为任意文本生成简短写实的标题和一两句话的描述，运行于 Apple 芯片。
为任意文本给出标题和描述。
一段讲用两部手机拍播客的片段，得到标题「Filming a two-person podcast on iPhone」，三到八个词，下面配一行描述。两者都不是人写的。
语气刻意保持平实：没有表情符号、没有话题标签、不做标题党，描述说的是这段文本是什么，而不是它的主题是什么。它在转写片段上微调，但用在一段新闻、一段产品描述或一封邮件上同样稳。
Title 仅在 Apple 芯片上运行，通过 MLX。加载一次即可反复使用；把它和 Clips 搭配，每个片段出来时都带着名字。
给每个片段命名
Clips 找出录音里的时刻，Title 给它们命名。一款创作者应用为每条短视频配上一个三到八个词的标题和一行描述，在手机上写好，什么都不发往别处。
笔记保存时就起好标题
一款笔记应用或语音备忘录应用，在条目保存的那一刻，就用它自己的文本给它起名。列表读起来像一份列表，而不是一列首行加时间戳。
为资料库描述一段录音
一款播客或课程应用在 Mac 上，根据转写文本写出这一集的标题和两句话的描述，随时可编辑。等有人来处理之前，这个字段不会一直空着。
灵感
用 Title 构建的点子。把提示词复制到你的编码 agent 里就能开始。
Auto-name and describe every clip and file.
Use Desert Ant's Title on-device to suggest a short title and a one-line description for a clip, note, or file from its text, so nothing is called 'Untitled'. Build it with the Desert Ant SDK. Title (Swift). Install and API: https://desertant.com/docs/title/. Install: SwiftPM desert-ant-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.
Title a note the moment it's saved.
In a notes app, run Desert Ant's Title on-device when a note is saved to propose a factual title and a short description, editable by the user. Build it with the Desert Ant SDK. Title (Swift). Install and API: https://desertant.com/docs/title/. Install: SwiftPM desert-ant-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.
Write library descriptions for a media archive.
Build a batch step that runs Desert Ant's Title on a Mac (Apple silicon) over transcripts in a media library to generate a title and description for each recording. Build it with the Desert Ant SDK. Title (Swift). Install and API: https://desertant.com/docs/title/. Install: SwiftPM desert-ant-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 a full podcast studio: transcribe, clip, and title on the device.
Build a podcast tool that runs Desert Ant's Voz to transcribe an episode, Clips to pick the best moments as shorts, and Title to name and describe each clip, all on-device with no per-minute or per-token bill. Build it with the Desert Ant SDK. Voz (Swift). Install and API: https://desertant.com/docs/voz/. Clips (Swift). Install and API: https://desertant.com/docs/clips/. Title (Swift). Install and API: https://desertant.com/docs/title/. SDK source: https://github.com/Desert-Ant-Labs/desert-ant-core. Machine-readable catalog of every model and SDK: https://desertant.com/llms.txt.
Draft an SEO title and meta description from a page's text.
Run Desert Ant's Title on a Mac (Apple silicon) over a page's content to draft a factual title and a one-to-two sentence meta description. Build it with the Desert Ant SDK. Title (Swift). Install and API: https://desertant.com/docs/title/. Install: SwiftPM desert-ant-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 a fully local clipping engine: transcribe, clip, title, caption.
Chain Desert Ant's Voz (transcribe with word timestamps), Clips (select the moments), and Title (name each clip) into a clipping engine that runs entirely on-device on iPhone or Mac, with word-accurate captions from Voz and no per-minute cost. Build it with the Desert Ant SDK. Voz (Swift). Install and API: https://desertant.com/docs/voz/. Clips (Swift). Install and API: https://desertant.com/docs/clips/. Title (Swift). Install and API: https://desertant.com/docs/title/. SDK source: https://github.com/Desert-Ant-Labs/desert-ant-core. Machine-readable catalog of every model and SDK: https://desertant.com/llms.txt.
A Shortcut that titles and describes whatever you share to it.
Build a Share-sheet App Intent that runs Desert Ant's Title on-device to suggest a title and a one-line description for shared text or a transcript. Build it with the Desert Ant SDK. Title (Swift). Install and API: https://desertant.com/docs/title/. Install: SwiftPM desert-ant-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 agent skill that titles and describes any file the agent makes.
On a Mac (Apple silicon), build a small Swift CLI that links Desert Ant's Title (MLX), then write a SKILL.md skill that calls it to give a clip, note, or transcript a short title and one-line description. Build it with the Desert Ant SDK. Title (Swift). Install and API: https://desertant.com/docs/title/. Install: SwiftPM desert-ant-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
- 一次调用，得到一个三到八个词、末尾不带标点的标题，以及一段一到两句话的描述。
- 刻意的平实语气：没有表情符号、没有话题标签、不做标题党。描述指认的是这段文本本身，而不是它的话题。
- 在转写片段上微调；用于一般散文（新闻段落、产品描述、邮件）同样有效。
- 直接为 Clips 输出的
Clip命名；每个片段一张卡片，顺序一致。 - 什么都不用下载。把模型文件放在应用旁边的一个文件夹里，再把那个文件夹传给 Titles；其他模型在首次使用时获取权重，这一个不用。
- 用 MLX 而非 Core ML：短文本生成实测在 GPU 上比在神经网络引擎上快 5.7 到 8.3 倍。一个量化到 6-bit 的 350M 参数模型，藏在
MLX包特性后面，加载一次即可反复使用。
示例应用
Clipper
使用 Voz, Clips, Title 构建
Generate short clips from a video podcast or a long recording, fully on device. A macOS app and a command-line tool over the same core.
Voz transcribes with a time on every word, Clips ranks the best spans, and Title writes a title and description for each.
macOS 26 or later, Apple Silicon
brew tap desert-ant-labs/tap
brew install --cask clipper快速上手
只需几行代码，即可为你的 iOS or macOS 应用加上 标题与描述。 Title 文档.
// Swift Package Manager
.package(url: "https://github.com/Desert-Ant-Labs/desert-ant-core.git", from: "3.1.0",
traits: ["MLX"])
// target dependency
.product(name: "Title", package: "desert-ant-core")import Title
let titles = try await Titles(directory: modelFolder)
let card = try await titles.describe(text)
card.title // "Filming a two-person podcast on iPhone"
card.description // one or two sentencesAdd Title from Desert Ant Labs to this Swift project (iOS, macOS).
What it does: Title：面向任意文本的设备端标题与描述.
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.git", from: "3.1.0",
traits: ["MLX"])
// target dependency
.product(name: "Title", package: "desert-ant-core")
Reference:
- Model page: https://desertant.com/models/title/
- 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
- 输出
- 一个 3 到 8 个词的标题和一段 1 到 2 句话的描述
- 模型
- 基于 granite-4.0-350m 微调，6-bit 量化，MLX
- 平台
- Apple 芯片上的 iOS、macOS、tvOS、visionOS（MLX）；没有 Android、Linux 或 Windows 构建
Title 尚在内部测试，模型卡里没有质量数据。目前还没有独立评审完成，模型有时会用它自己指令所禁止的套话来开头描述。在输出到达用户之前先读一遍。仅支持 Apple 芯片，通过 MLX 运行。请使用 SDK 自带的提示词：模型是按一条指令训练的，换一种措辞会让输出变差。
常见问题
Title 是什么？
设备端标题与描述：为任意文本生成简短写实的标题和一两句话的描述，运行于 Apple 芯片。
Title 在设备上运行吗？
是的。Title 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。
Title 支持哪些平台？
Title 以面向 Swift 的原生设备端 SDK 形式提供。
Title 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。