# On‑Device AI:Private Workspace — Private Chat, Voice & Research

> Private AI assistant for transcription, multi-agent collaboration, and web automation. (iPhone/iPad app by Zijie Deng.)

- Source: https://appshunter.io/ios/app/ondevice-aiprivate-workspace/id6497060890 (this page in markdown: same URL + `.md`)
- Developer: [Zijie Deng](https://appshunter.io/developer/1070117038)
- Category: Utilities, Productivity
- Price: Free with in-app purchases
- Rating: 4.40/5 from 161 App Store ratings · 107 written reviews indexed
- Age rating: 17+
- Requires: iOS 18.0 · 1.8 GB
- Languages: American English, Dutch, French (France), German (Germany), Italian, Japanese, European Portuguese, European Spanish, Chinese (Traditional, Taiwan)
- Released: 2024-04-17
- Data updated: 2026-08-22
- Monetization: free with in-app purchases
- User reviews in markdown: https://appshunter.io/ios/app/ondevice-aiprivate-workspace/id6497060890/reviews.md

## What is On‑Device AI?

On-Device AI puts chat, listening, transcription, notes, and research in one private app for iPhone, iPad, Mac, and Apple Vision Pro. Your data stays on your device.

Download a model once and the app keeps working on a plane, on the subway, or with no signal at all. Your chats, documents, recordings, and notes are processed and stored on your device. Online providers and web features are there when a task needs them, and only after you switch them on.

ONE APP, TEN WORKSPACES
AI Chat, AI Search, AI Browser, Listen Library, RSS Feeds, Voice Note, Text to Speech, Knowledge, Text Note, and App Help all share the same models and the same private storage.

AI CHAT
Chat with local or cloud models.
• Run local models from families such as Gemma, Qwen, DeepSeek, and Mistral, or connect your own provider account
• Pick models that fit your device, including ones for text, vision, reasoning, and tools
• Drop in documents and images, fork any conversation, and compare several models on the same prompt
• Let the model use tools for calculations, web requests, documents, Calendar, and Reminders, and review proposed changes before they apply
• Build Agent Profiles, add AI Skills, connect MCP servers, and run subagents when a job takes several steps
• Keep facts you repeat often in Global Memory

LISTEN LIBRARY AND RSS FEEDS
Read less, listen more.
• Turn PDFs, Markdown, plain text, web articles, and scanned books into a listening queue
• Scan photographed pages, correct the OCR the app runs on device, and keep each page with its spoken text
• Follow sites through RSS, Atom, and JSON feeds, then send articles to Up Next
• Choose Apple voices or local neural voices, follow along in the reader, and set a sleep timer

VOICE NOTE, VOICE TYPING, AND TEXT TO SPEECH
Speak instead of typing, and listen instead of reading.
• Record and transcribe meetings, lectures, interviews, and quick ideas
• Dictate with Voice Typing on Mac or the voice keyboard on iPhone and iPad
• Transcribe with Apple Speech, Whisper, Parakeet, Nemotron, Qwen3-ASR, and other engines
• Turn text, or text captured from a photo, into audio with Apple voices, Kokoro, PocketTTS, Qwen 3 TTS, CosyVoice, and VibeVoice
• Export transcripts as text, subtitles, or Markdown

AI SEARCH AND AI BROWSER
Research with a second pair of hands.
• Search the web in a conversation and let the model read the results for you
• Browse with tabs, profiles, history, and downloads, then ask your model to read, assist, or act on the page
• Hand a task to the browser agent, watch each step, and take over whenever you want

KNOWLEDGE AND TEXT NOTE
Give your AI your own material to work from.
• Add PDFs, text, Markdown, code, images, and website content to a private searchable library
• Write and edit Markdown notes in the app
• Import AI chats, voice notes, Text to Speech items, and AI Search results
• Tune retrieval and index edited content again

APP HELP
Ask how a feature or setting works. App Help answers from a guide that ships inside the app, keeps help out of your saved chats, and points to the right settings.

MADE FOR APPLE DEVICES
• Widgets for Listen, Voice Note, Text Note, and Quick Actions
• Siri, Apple Shortcuts, App Intents, the Mac menu bar, and keyboard shortcuts you can customize
• Apple hardware acceleration for supported local models
• Store models internally, on an external drive, or on a shared volume
• On Mac, connect messaging apps so your model can draft or send replies under rules you set
• Interface in English, Dutch, French, German, Italian, Japanese, Spanish, Portuguese, and Traditional Chinese

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

## Key features

- Speaker Diarization for meeting transcripts
- Real-time live transcription
- Natural AI speech generation
- Deploy specialized AI subagents
- AI-powered web browser automation
- Control AI via messaging apps
- 100% offline processing option

## Pricing and in-app purchases

Base price: Free.

**Subscriptions**

| Subscription | Price | Period |
| --- | --- | --- |
| Pro Member Subscription | $34.99 | per year |
| Pro Member Subscription | $3.99 | per month |

**One-time purchases**

| Purchase | Price | Type |
| --- | --- | --- |
| Lifetime Pro Member | $49.99 | one-time |
| Lifetime Pro Member | $99.99 | one-time |


## What do users think of On‑Device AI?

Overall sentiment: positive

**Pros**

- 🚀 Game-changing AI assistant
- 🔍 Powerful search functionality
- 👍 Customizable and versatile
- 🌐 Seamless multi-device experience
- 💡 Innovative character-based interactions

**Cons**

- 🐛 Crashes on larger models
- 🔋 Heating issues on some devices
- 🔍 Slow and unreliable web search
- 💻 Buggy on macOS

**Commonly reported bugs**

- Crashes on startup
- Model selection issues
- Inability to copy generated text

**Most requested features**

- Automated multi-character conversations
- Character set saving and syncing
- Streamlined search integration
- UI optimization for icons
- Remote endpoint support for multi-agents
- HomeKit integration
- Improved documentation
- Enlarged agent input window
- Per-agent model assignment

## Recent user reviews (10 of 107)

All indexed reviews: https://appshunter.io/ios/app/ondevice-aiprivate-workspace/id6497060890/reviews.md

### 5/5 — Great app! Great dev!

*2026-07-12, version 1.46.0*

Dev is very responsive! Constantly improving!

### 1/5 — still full of bugs

*2026-07-10, version 1.46.0*

the voice mode is still mot working right, the interface is horribly bad design, it crashes every 5 minutes etc... no response from the developer... skip this! there are many AI client apps out there that actually work.

### 5/5 — incredibly capable

*2026-06-07, version 1.44.0*

Well done!

### 5/5 — Importing your own models is amazing!

*2026-05-24, version 1.43.0*

I love the ability to add your own mlx or gguf models!

### 1/5 — crash crash crash

*2026-05-23*

an other update with hopes crushed by constant crashes, voice mode crashes when you use the auto mode after the first answer, it does not switch into listening mode, just simply crashes no matter what voice model or ai model you use... on an M2 ipad pro with 16 gigs of ram... this app was never stable, pretty much unusable, no response from developer... don't spend money on this app, not worth it until they fix the bugs instead of packing more and more features into it.

**Developer response:** Hi trancemuter, thank you for using the app. We apologize for the inconvenience. It was a bug that has now been fixed in the latest version. 

You should be able to long-press and copy the model response in iOS, and select text on macOS. Please update to the newest version to try it out.

### 1/5 — Crashes and crashes the whole iPad

*2026-05-13, version 1.42.0*

Nobody needs this! Not only does it crash it takes down the whole system. This is a POS.

### 5/5 — High quality and well thought out

*2026-04-20*

Excellent implementation of features and very robust.  This app is more advanced than most which allows you to do so many neat things. Highly recommend to pay the small fee and unlock everything

**Developer response:** Thank you for supporting!

### 1/5 — hard crash!!!

*2026-04-14*

today I saw that there is an update, I was happy to try it out, maybe they fixed the problems it had, I sent emails to them about it, (no response btw) well, I open it up and starts loading the last model I was using then hard crashed immediately, not just a normal crash, it was blank screen crash!!! it was stuck on blank screen for a while unresponsive to anything, then my iPad restarted by itself, thanks God! this is the only app that hard crashes my iPad and I have over a thousand apps, I even beta test apps, I am a power user, no other app ever crashed my iPad as this app is crashing it, not only now, this app had these hard crashes many time despite the updates!  I have a maxed out iPad pro M2, 16gb ram 2 tb storage, I have about 700 gigs free space on it, I was only running this app on a freshly restarted machine... this is not normal! idk what else to say but this developer is not a pro! no response from support either for weeks now, I have a lifetime membership... I think there is a new owner or something, I had good working relationship with the developer before, I was testing for them, he was responsive to me before, not anymore... yeah... 🤷‍♂️ idk...

**Developer response:** Hi trancemuter, thank you for using the app. We apologize for the inconvenience. It was a bug that has now been fixed in the latest version. 

You should be able to long-press and copy the model response in iOS, and select text on macOS. Please update to the newest version to try it out.

### 3/5 — Corrupted

*2026-04-11, version 1.39.0*

OK I fished my crashing issue. Seems he model I tried was too large. But I'm trying gemma 4 GGUF and it's saying it's corrupt 
. What's going on?

### 4/5 — One of the best.

*2026-03-29, version 1.39.0*

Update:
Please add a guide for the newest agent features as I dont know where to find them, or get them working.  is there a page that indicates features?




old: 
Cant get the search to work as all the LLMs I have tried all say DuckDuckGo or Bing dont have any information or that the page is just the search engines privacy policy or some error happens (AI_on_Device.WebBrows…

If this did work it would be a 5 star app for sure. 
It also seems to be missing the huggingface search that other apps are starting to include which gives a good option to search model cards and find specific quantizations.
Though it is really awesome that MLX models are offered in the downloads area.

I like the UI, though the sidebar buttons sometimes lag or dont register taps.

I’d buy lifetime if this had Kokoro and/or VITS text-to-speech.

## Frequently asked questions about On‑Device AI

### What does On-Device AI do?

On-Device AI transforms your Apple device into a private AI powerhouse. It offers advanced language models, professional voice transcription, natural speech generation, and multi-agent collaboration. You can use it for tasks like mastering meetings with speaker diarization, deploying specialized subagents for complex work, and controlling your AI through messaging apps, all while maintaining complete privacy.

### What are the key features of On-Device AI?

Key features include speaker diarization to identify speakers in recordings, flawless live transcription for meetings, and natural AI voices for speech generation. It also allows you to deploy expert subagents for tasks like research and writing, automate web browsing, and control your AI remotely via messaging apps like Slack and Telegram. A significant feature is its 100% offline processing capability.

### Is On-Device AI free to use?

The application is free to download and use, offering core functionalities. However, it operates on a 'free with in-app purchases' model. This means that while you can access many features without cost, certain advanced capabilities, premium models, or expanded usage might require in-app purchases.

### What devices is On-Device AI compatible with?

On-Device AI is designed to run directly on your Apple devices. This includes your Mac, iPad, and iPhone. The app leverages the hardware capabilities of these devices to provide its advanced AI and speech processing features, with specific optimizations for iOS and macOS.

### Can I use On-Device AI for sensitive information?

Yes, the app is built with privacy as a core tenet, offering a 100% offline processing option. This means sensitive documents and data can be processed entirely on your device without being sent to any cloud servers, ensuring total security and confidentiality.

## Version history (last 5 releases)

### 1.48.0 — 2026-08-19

Version 1.48.0 adds AI Browser, chats that survive interruptions, MCP servers, and much more control over your models and memory.

• AI Browser: Browse with tabs, profiles, history, downloads, and restored sessions, then ask your current model to read the page, help you with it, or act on it. The app tells you what a site can see and asks before anything changes outside the app.
• Browser tasks that finish: Switch models before a task, follow a clearer timeline of what the agent did, and resize the task pane on Mac. Page reading and action checks improved, the app notices when a task is going in circles, and results are better on long or complex sites.
• Chats that survive interruptions: A reply keeps going and reconnects if you navigate away. Queue your next prompt with Send Next or Stop & Send, and compare several models against the same frozen input.
• Agent Profiles, schedules, and MCP: Create agent workspaces that stick around, run them when you want, or put supported work on a schedule. Connect remote MCP tool servers and install reviewed AI Skills that cannot run code, while you stay in charge of which tools are on.
• Settings for each agent: Give individual Flow Agent steps and Subagents their own temperature and context window, or let them inherit your conversation defaults.
• One place for model storage: See how much space chat, embedding, speech, and voice models use. Recover interrupted downloads and safely review duplicate, legacy, incomplete, or orphaned files.
• Global Memory you can manage: Search, filter, pin, edit, delete, and undo memories in their own settings area. When the AI wants to change a memory, it now asks the same way tools do.
• Faster recovery: Reload your last chat model in one step, and keep a conversation ready when reading aloud borrows a speech engine or restores a model afterwards.
• Help, settings, and tools: App Help understands plain questions and comparisons better, support drafts open in more email apps, Settings sections respond faster, and local GGUF and MLX models recognize tool calls more reliably.

### 1.47.0 — 2026-08-04

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.

### 1.46.0 — 2026-07-09

Version 1.46.0 adds Calendar and Reminders tools, a faster Text Note workspace, stronger AI Search, and more Shortcuts support.

• Calendar and Reminders tools: With your permission, AI tools can read, create, update, complete, move, and delete events or reminders after you review changes.
• Text Note workspace: Create a note quickly, pick the Knowledge Library it belongs to, edit in a cleaner notes view, and keep it searchable.
• Cleaner AI Search context: Web results now skip consent pages, cookie notices, search-engine boilerplate, and other unusable pages, with fallback behavior when a result set is noisy.
• Save AI Search results: Import a completed AI Search answer into a Knowledge Library as a curated Markdown snapshot with the query, answer, sources, and supporting context.
• Smarter note destinations: When you use multiple Knowledge Libraries, the app asks where a new note should go instead of creating duplicate default libraries.
• Customizable side menu: Choose which sections stay pinned in the sidebar and open everything else from the new Menu.
• More Shortcuts actions: Transcribe audio files, speak text, export generated audio, and create Text Notes from Apple Shortcuts or Siri.
• Better TTS playback: Kokoro long-form playback now keeps generated segments tied to the active session, so restarts and cleanup behave more reliably.
• Safer Calendar & Reminders permissions: Actions require explicit permission, personal-data consent, and a review step before changes are applied.
• Fixes and improvements: Improved Text Note selection, autosave/status feedback, keyboard behavior, and sidebar navigation.

### 1.45.0 — 2026-06-23

Version 1.45.0 makes voice typing faster, files easier to add, and Knowledge Libraries more useful.

• Faster voice typing: Clearer controls, quick language and model selection, Quick Paste, and live progress while you record.
• Drag and drop files: Drop documents and images straight into a chat or a Knowledge Library, or paste them in.
• Notes in Knowledge Libraries: Write and edit Markdown notes in the app, preview the formatting, and keep the search index current.
• Re-transcribe recordings: Run a saved recording again with a different model, language, or speech enhancement, and cancel anytime.
• Choose what loads at launch: Pick a model or provider to prepare on startup, or open the app with nothing loaded.
• Batch actions: Select multiple chats, Voice Notes, or Text to Speech items to delete them or add them to a Knowledge Library.
• More room to type on iPhone and iPad: The prompt editor expands when the on-screen keyboard is open.
• Better Shortcuts and App Intents: Find and open conversations, libraries, and documents from Apple workflows.
• Polish and bug fixes: Smoother navigation, clearer model status, and better attachment handling.

### 1.44.1 — 2026-06-08

Version 1.44.1 makes On-Device AI easier to use globally and smoother for everyday voice work.

• Multi-language support: The app now has broader language coverage. Please send suggestions or wording feedback to developer@ondevice-ai.app.
• Better STT and TTS voice enhancement: Speech-to-text and text-to-speech workflows are more reliable, with improved handling around voice enhancement.
• Faster chat UI: Conversation screens have been optimized for smoother scrolling and more responsive long chats.
• Clearer TTS generation UI: Text-to-speech generation now gives a better visual flow while audio is being prepared.
• Improved model downloads: TTS and STT model downloads are easier to follow and more stable.
• Bug fixes and polish: Includes smaller fixes across voice, chat, and model workflows.
• Fixed an issue where the keyboard could block the input field.
• Fixed an issue that could prevent vision models from loading.

## Apps similar to On‑Device AI

| App | Rating | Price | Category |
| --- | --- | --- | --- |
| [xChat AI - Offline Chatbot](https://appshunter.io/ios/app/xchat-ai-offline-chatbot/id6499191724) | 3.7 (3) | Free | Utilities |
| [Private LLM - Local AI Chat](https://appshunter.io/ios/app/private-llm-local-ai-chat/id6448106860) | 4.1 (702) | $4.99 | Utilities |
| [PrivAI - Private AI GPT Chat](https://appshunter.io/ios/app/privai-private-ai-gpt-chat/id6654888355) | 4.8 (4) | Free | Utilities |
| [fullmoon: local intelligence](https://appshunter.io/ios/app/fullmoon-local-intelligence/id6727014156) | 4.4 (100) | Free | Utilities |
| [LLM Local Client](https://appshunter.io/ios/app/llm-local-client/id6738433730) | 4.6 (5) | Free | Utilities |
| [Liquid Apollo](https://appshunter.io/ios/app/liquid-apollo/id6448019325) | 4.5 (599) | Free | Utilities |

## More apps by Zijie Deng

- [Pretty Penny](https://appshunter.io/ios/app/pretty-penny/id1070117039)
- [Wifi - Manager](https://appshunter.io/ios/app/wifi-manager/id1117194115)
- [JS.Notebook](https://appshunter.io/ios/app/jsnotebook/id1470144639)

All apps by Zijie Deng: https://appshunter.io/developer/1070117038

## Related topics

[zijie deng](https://appshunter.io/ios/topics/zijie-deng) · [on-device ai](https://appshunter.io/ios/topics/on-device-ai) · [mlc chat](https://appshunter.io/ios/topics/mlc-chat) · [ai private notes](https://appshunter.io/ios/topics/ai-private-notes) · [llm farm](https://appshunter.io/ios/topics/llm-farm)

---

*Data collected daily from the US App Store and indexed by [AppsHunter](https://appshunter.io/). User reviews are verbatim App Store reviews. Ratings, prices and chart positions refresh continuously; this snapshot is from 2026-08-22.*
