Title.
On-device titles and descriptions: a short factual title and a one or two sentence description for any passage, on Apple silicon.
Suggest a title and description for any text.
A clip about shooting a podcast on two phones gets the title "Filming a two-person podcast on iPhone", three to eight words, with a one-line description under it. Nobody typed either one.
The register is deliberately plain: no emoji, no hashtags, no clickbait, and the description says what this passage is, not what its subject is. Fine-tuned on transcript clips, and it holds up on a news paragraph, a product description, or an email.
Title runs on Apple silicon only, through MLX. Load it once and reuse it; pair it with Clips and every clip leaves with a name.
Name every clip
Clips finds the moments in a recording; Title names them. A creator app posts each short with a title of three to eight words and a one-line description, written on the phone, with nothing sent anywhere.
Title a note as it's saved
A notes app or a voice memo app names the entry from its own text the moment it is saved. The list reads like a list instead of a column of first lines and timestamps.
Describe a recording for the library
A podcast or lecture app writes the episode title and the two-sentence description from the transcript on a Mac, ready to edit. The field is never blank until someone gets to it.
Inspiration
Ideas to build with Title. Copy a prompt into your coding agent and go.
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.
What the model does
- A title of three to eight words with no final punctuation, and a description of one or two sentences, from one call.
- Plain register on purpose: no emoji, no hashtags, no clickbait. The description identifies this passage rather than its topic.
- Fine-tuned on transcript clips; works on general prose (news paragraphs, product descriptions, emails).
- Names a
Clipfrom Clips directly; one card per clip, in the same order. - Nothing is downloaded. Ship the model files in a folder with the app and pass that folder to Titles; the other models fetch their weights on first use, this one doesn't.
- MLX rather than Core ML: short generation measured 5.7-8.3x faster on the GPU than on the Neural Engine. A 350M-parameter model quantized to 6-bit, behind the
MLXpackage trait, loaded once and reused.
Example app
Clipper
Built with Voz, Clips, Title
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 clipperGetting started
Add titles and descriptions to your iOS or macOS app in a few lines of code. Title docs.
// 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: On-device Titles and Descriptions for Any Text.
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.
Specs
- Output
- A 3 to 8 word title and a 1 to 2 sentence description
- Model
- Fine-tuned from granite-4.0-350m, 6-bit quantized, MLX
- Platforms
- iOS, macOS, tvOS, visionOS on Apple silicon (MLX); no Android, Linux, or Windows build
Title is in internal testing and its card carries no quality figures. No independent review has been completed, and the model sometimes opens a description with a stock phrase its own instruction forbids.
Read the output before it reaches a user. Apple silicon only, through MLX.
Use the SDK's own prompt: the model was trained on one instruction, and a reworded one gets worse output.
FAQ
What is Title?
On-device titles and descriptions: a short factual title and a one or two sentence description for any passage, on Apple silicon.
Does Title run on device?
Yes. Title runs on the device, with no server call, so the data stays with the user.
Which platforms does Title support?
Title ships as a native on-device SDK for Swift.
How much does Title cost?
Every model is free up to 100k monthly active devices per SDK. Unlimited inference per user. Contact us for custom licenses.