On-Device AI: Private Suite

On-Device AI is a private workspace for chat, voice, documents, listening, notes, research, and automation on iPhone, iPad, Mac, and Apple Vision Pro. Local models can work fully offline. Cloud providers and web tools are available when you choose to use them.

PRIVATE BY DEFAULT

Your conversations, documents, transcripts, and local model runs stay on your device. Enable an online provider or web tool when a task calls for one.

• Run local models from families such as Llama, Gemma, Phi, Qwen, DeepSeek, Mistral, and Nemotron

• Choose text, vision, reasoning, and tool-capable models that fit your device

• Store models internally, on an external drive, or on a shared volume

• Use local speech recognition, text-to-speech, OCR, and document search

• Add cloud providers when a task calls for them

BUILD A LISTENING LIBRARY

Turn documents and articles into a reading and listening queue you can take with you.

• Add PDFs, Markdown, plain text, readable web articles, and scanned books

• Scan or import photographed pages, correct the on-device OCR, and keep each page with its spoken text

• Subscribe to RSS, Atom, and JSON feeds, or browse suggested feeds when you need a place to start

• Add feed articles to Up Next and keep your place as you read or listen

• Choose Apple voices or supported local neural voices

• Follow playback progress, adjust narration, and set a sleep timer

TALK, TRANSCRIBE, AND CREATE AUDIO

Capture ideas, meetings, and passages privately.

• Use Voice Typing on Mac or the voice keyboard on iPhone and iPad

• Record and transcribe meetings, lectures, interviews, and voice notes

• Import audio or transcribe it again with another model or language

• Choose Apple Speech, Whisper, Parakeet, Nemotron, Qwen3-ASR, and other supported engines

• Turn typed text or text captured from an image into speech

• Create audio with Apple voices, Kokoro, PocketTTS, Qwen 3 TTS, CosyVoice, and VibeVoice

• Export transcripts as text, subtitles, or Markdown

CHAT WITH YOUR OWN AI

Use a local or cloud model, bring in your own material, and shape the conversation around the task.

• Choose, paste, or drag documents and images into a chat

• Fork a conversation from any message while keeping the original

• Switch models, tools, roles, and reasoning options as the task changes

• Build specialist agents and run subagents for multi-step work

• Copy or export full conversations

BUILD A PRIVATE KNOWLEDGE LIBRARY

Make files, notes, chats, and transcripts searchable context for your AI.

• Add PDFs, text, Markdown, code, images, and website content

• Write and edit Markdown notes inside the app

• Import AI chats, voice notes, Text to Speech items, and AI Search results

• Search larger libraries, tune retrieval, and re-index edited content

RESEARCH AND USE TOOLS

Search the web in a conversation, let the browser agent gather information, or take over yourself. Tools can handle calculations, network requests, documents, Calendar, and Reminders. For Calendar and Reminders, the app shows proposed changes before applying them.

HELP WHEN YOU NEED IT

Ask App Help how a feature or setting works. It combines the active model with a built-in guide to On-Device AI, keeps help separate from saved chats, and points to relevant settings when useful.

MADE FOR APPLE DEVICES

• Add widgets for Listen, Voice Note, Text Note, and Quick Actions

• Resume listening, play what is next, open RSS Feeds, or start a note with fewer taps

• Use Siri, Apple Shortcuts, App Intents, the Mac menu bar, and customizable keyboard shortcuts

• Choose an app language, with expanded interface support for Dutch, French, German, Italian, Japanese, Spanish, Portuguese, and Traditional Chinese

• Use Apple hardware acceleration with supported local models

EULA: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/