On-Device AI: Private Suite

About this app

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/

Version 1.47.0 adds a new Listen Library, RSS Feeds, App Help, and widgets. • Listen Library: Turn PDFs, Markdown, text files, readable web articles, and scanned books into a personal reading and listening queue. Keep your place, manage Up Next, and use the new sleep timer when listening at night. • Scanned books and image text: Scan or import photographed pages, review and correct the on-device OCR, then save the result as a book that keeps each page beside its spoken text. Text to Speech can also capture a passage from an image. • RSS Feeds: Follow RSS, Atom, and JSON feeds inside the app, browse curated suggestions, and build a listening queue from sources you choose. • App Help: Ask how a feature or setting works in a focused help chat backed by the app's built-in guide. App Help can point you to the right settings while keeping help questions separate from your saved chats. • New widgets: Add Listen, Voice Note, Text Note, or Quick Actions widgets on iPhone, iPad, and Mac. Resume playback, play the next item, open RSS Feeds, or start a note with fewer taps. • Better multilingual support: Expanded interface translations and more consistent language handling throughout the app. Widgets follow the language selected in On-Device AI. • More model choices: The built-in catalog now includes more ready-to-download models, including Gemma 4 QAT options, Devstral Small 2, Nemotron 3 Nano, Qwythos. • Smoother speech workflows: Long Kokoro Speak Text shortcuts can begin playback sooner. Shortcuts also recognize your paid model access more reliably when they start the app in the background. • Fixes and polish: Improved Listen imports, page editing, OCR review, reader layouts, playback handoff, feed discovery, and App Help navigation.

Momentum comes from crawler snapshots for the tracked storefront. “Viral growth signal” means unusually fast recent rating gains; it is an indicator, not download data.

1. First observed Aug 1, 2026 · 1:25 PM Free