Privacy AI: Agent & Chatbot

Privacy AI: Agent & Chatbot

GGUF/MLX, voice, image, skills

21 ratings
13 reviews
Free
In-App Purchases

Details

Released
July 18, 2025
Updated
November 5, 2026

Features

Privacy AI: Agent & Chatbot video #1 for iPhone
Privacy AI: Agent & Chatbot video #2 for iPhone
Privacy AI: Agent & Chatbot screenshot #3 for iPhone
Privacy AI: Agent & Chatbot screenshot #4 for iPhone
Privacy AI: Agent & Chatbot screenshot #5 for iPhone
Privacy AI: Agent & Chatbot screenshot #6 for iPhone
Privacy AI: Agent & Chatbot screenshot #7 for iPhone
Privacy AI: Agent & Chatbot screenshot #8 for iPhone
Privacy AI: Agent & Chatbot screenshot #9 for iPhone
Privacy AI: Agent & Chatbot screenshot #10 for iPhone
Privacy AI: Agent & Chatbot screenshot #11 for iPhone
Privacy AI: Agent & Chatbot screenshot #12 for iPhone
iphone
iphoneDuo
ipad
πŸ–ΌοΈGet Icon
Iconsβ†˜οΈŽ

About

This AI toolkit offers a comprehensive suite of tools for local and cloud-based models, including language, speech, and image processing. It enables users to chat, run agents, transcribe meetings, and generate images with over 60 integrated functions. Local model features operate entirely offline, enhancing privacy and accessibility.

βœ“Local and cloud AI model integration
βœ“AI agent with goal-driven planning
βœ“Speech recognition and text-to-speech
βœ“On-device image generation
βœ“Meeting transcription and summarization
βœ“AI-powered writing and editing tools
βœ“Document scanning and conversion
Show original description
+1

What's New in Privacy AI

3.4.2

November 5, 2026

New in 3.4.2: import a novel and keep writing it. Recover, rewrite or translate the whole book, or start a short story from a brief. FEATURES - Recover and Rewrite Imported Novels: chapters, characters, open threads and the story so far are rebuilt step by step. Rewrite from any chapter, or start a new story in its world. - Translate a Novel: a whole book into another language as a new project, after you check names and terms. - Short Stories: write scene by scene from a brief, with a review of the finished story. - Use Models Where They Are: link a model folder or file, even on an external drive. Models are used in place and never deleted on Remove. - Reader on Home and Share: open Reader from Home, send it links, text or files from other apps, and import from Google Drive (Pro). - Save Designed Voices: save any take in Voice Clone's Design step as an audio file. IMPROVEMENTS - Hide a Pane or Go Full Screen: side by side views such as Reader and Meetings hide one side or go full screen from the "..." menu. - iPad: the sidebar stays pinned in landscape, and Tools, Reader and local model lists show details beside the list. - GPT-5.6 and GPT-6 (Luna, Sol, Terra, Astra) work in chats and with tools. - Grok Sign-In is back in API Keys, including from Safari on iPhone and iPad. - Text to Audio: the screen stays on while converting, and you can listen to finished parts while it runs. - Steadier Long Stories: chapters land closer to your length, dates stay consistent, and characters sound more distinct. - Polish Suggestions You Choose: keep or skip each edit, undo a repolish, and turn thinking on per project. - New models: LFM3-1.7B, LFM3-VL-2B and Nemotron 3 Nano 4B, in a new "New" category. - Faster engines: llama.cpp v0.8.0 and MLX run faster and use less memory. - Thinking on MLX stays in the thinking area, and voice mode never reads it aloud. - New voices: Phonon 31M (also on the Neural Engine) and VoxCPM 1.5, which clones a voice from a short clip. - Qwen3-TTS keeps one voice on long text, and cloned voices speak faster. - Long voice samples are trimmed at a natural pause automatically. - iOS Speech API is marked Online, since audio may go to Apple's servers. BUG FIXES - Model settings no longer save when you only open and close them. - GGUF models get their chat format as trained, so Ministral 3 Reasoning calls tools reliably and LFM3 answers correctly. - Errors show the provider's real reason; tables and Knowledge Wiki pages display cleanly. - Failed Reader imports offer Try Again, and iCloud chats show their titles. - Thinking models no longer return empty outlines or chapters, and outline glitches no longer stop a book. - Parakeet transcripts are cleaner, dictation stops right away, and Qwen3-TTS and Pocket TTS play cleanly. - Voice detection works offline. - Cloned voices from your other devices download instead of failing. - Text to Audio lists your cloned voices for Qwen3-TTS Base. - Transcription falls back to on-device recognition when your model is missing. Open Novel Writer, import your manuscript, and pick up where you left off.

More
2

Subscriptions & In-App Purchases

Weekly Pro Plan

Subscribe to the Privacy AI Weekly Plan

$3.997 Days
How to cancel Privacy AI subscription ⁉️

Events

Read more about Rethink: Resume AI Reasoning

Rethink: Resume AI Reasoning

Resume analysis without rerunning tools

Dec 19, 2025 β€” Dec 30, 2025

User reviews

Right direction

**Edited: Dev responded positively and implemented fix right away, 5*

Overall, I think this is on the right track, though one obvious problem is the text-to-speech feature... what's called "File TTS" isn't actually text to speech.... it's ASR/STT. That label should be corrected.

On top of that, there's already a way to input text and preview how it sounds using the TTS models, so I don't understand why that same option isn't available for other text I'd want converted.

Paying an API provider to run some massive model makes no sense to me when my own device has plenty of processing power for the job, and the drop in quality would be perfectly tolerable.
Show more

Response from developer

Thanks for the honest review, and you are completely right about that label. That tab is for file transcription, so it is ASR, not text to speech. Calling it "File TTS" was my mistake. It is now "File ASR" and the fix is in the next update. Your second point is a fair hit, and the credit is yours: I had not thought of it. You were right that it made no sense for the local voices to work in the preview box with no way to point them at anything else. The pieces turned out to be mostly there already and just needed wiring together, so I built it. There is now a "Text to Audio" feature that turns any text or document into an audio file using the speech models already on your device, processed in chunks so a long article or a book chapter works fine, and you can resume one you stopped partway. It ships in the next update. I agree with you on the last point. The phone has plenty of power for this job, the local voices sound good enough, and nothing needs to leave the device or cost anything to run. Thanks for taking the time to write this up.

Hands down one of the best iOS harness/inference clients.

Top two alongside Minis. You really can’t ask for more when it comes to running AI on iOS, and the development team is constantly pushing newer and newer updates on a regular basis. Just when you think it couldn’t possibly get better, they outdo themselves yet again.

Now this is how app development SHOULD be like. Major respect to the team, and thank you. Infinitely appreciated.
Show more

Response from developer

Thank you so much for this. This kind of message is what makes the work worth it. It means a great deal to hear that the regular updates are landing well. My goal has always been to make running AI on iOS feel simple and private, and to keep improving it with every release. I have plenty more planned, and reviews like yours are exactly what keeps the momentum going. If you ever run into something you would like to see improved or added, I would love to hear it. Thank you again for the kind words and the support.

Excellent

This app is useful to me because it allows me to understand the capability of my device. Privacy AI is a little bit crowded, but that’s only because it lets you do everything under the sun. Because of this app, I know what models I will be using in apps I am building.

Response from developer

Thanks so much for the kind review, and for the five stars. I love that you use Privacy AI to see what your device can really do. That is exactly what I hoped for: a private place to try models hands-on before you pick one for your own apps. Fair point on it feeling crowded. It got that way because I wanted to fit in as much as I could. I am always working to make it easier to get around. If something ever feels buried, just let me know. Thanks again for the writing.

What’s in a name?

Using the app so far has been pretty mind blowing. Every other local inference wrapper application has a long way to go before they even touch the capabilities of this thing. It’s nothing shy of ambitious. I just wonder how they devs could put so much thought into the product itself but yet have such a…lackluster name. Anyways, top marks ti the mysterious makers of this masterpiece.
Show more

Response from developer

Thanks for the kind words, really glad the capabilities have impressed you! You are complete correct about the app's name. When I chose the name, I just wanted to express the idea that privacy protection is at the core of the app. But after it went live, I realized there are quite a few apps with similar names on the App Store, which makes it hard to find mine. I will admit that was a bad call on my part. Appreciate the top marks regardless. Thank you!

Very cool app

Has solely a subscription rather than one time payment in-app as an option and also collects tracking data, any data collection beyond typical LLM API usage makes the name pretty ironic. I get the purpose of the subscription model, and without a one time purchase it segments the potential customers into subscribers and those that will just pass on it entirely.

Analytics are enabled by default too, so it is requiring users to opt-out by default. These can change in the future but show the direction to begin with and are often followed by typical dev review replies with attempted justifications. Doesn’t escape the contradictory.

Solid UI.
Not a lot of justification in contrast, no thanks.
Show more

Response from developer

You are right that "Privacy AI" sets a high bar, and I want to address your points honestly rather than talk past them. On analytics: the app has no server and requires no account registration. Your conversations, your AI outputs, and your API keys never leave your device. The only third-party data collection is Google Analytics, which captures aggregate feature usage, things like which features are popular and how often certain screens are visited. It does not touch your conversations or any personal content. I acknowledge the contradiction: even aggregate analytics sits uneasily under a privacy-focused name, and I understand why that bothers you. If you prefer no data is sent at all, you can disable analytics entirely in Settings and nothing will be transmitted. If you want to go further and verify that yourself, the app has built-in proxy support for mitmproxy and Charles. You can route all traffic through either tool and audit exactly what is sent out in plain text. Or if you prefer, you can use any network traffic monitoring software you trust, such as Wireshark, to inspect the same data independently. I am comfortable saying that openly because I have nothing to hide there. On the subscription: A lifetime purchase model would pull my attention toward supporting a growing base of one-time buyers rather than building new features. The subscription keeps me focused on the things that actually make the app better for everyone using it. Thank you for the kind words on the UI. That means a lot. If you have more questions or want to dig into any of this further, feel free to reach out at customercare@acmeup.com, on Discord, or on X at @best_privacy_ai. I am happy to talk through it.

FAQ

What is Privacy AI?

Privacy AI is an all-in-one AI toolkit that supports local and cloud-based models for language, speech, and image processing. It allows users to chat, run agents, transcribe meetings, and create images with over 60 tools, with many local features working offline.

Does Privacy AI have ads?

No, Privacy AI is free to use and does not contain advertisements. The app emphasizes a clean user experience without interruptions from ads.

Can I use Privacy AI offline?

Yes, local model features in Privacy AI work fully offline. This includes local language models, speech recognition, and image generation, ensuring privacy and accessibility without an internet connection.

What kind of AI models does Privacy AI support?

Privacy AI supports a wide range of models, including local GGUF, MLX, and Core AI models, as well as Apple's on-device and Private Cloud Compute models. It also connects to major cloud providers like OpenAI, Claude, and Gemini.

How does Privacy AI handle sensitive text?

Privacy AI's Smart Chat routes messages by complexity and keeps sensitive text local. This ensures that your private information remains on your device, enhancing security and privacy.

What are the subscription options for Privacy AI?

Privacy AI offers several subscription plans: a Weekly Pro Plan for $3.99, a Monthly Pro Plan for $9.99, and a Yearly Pro Plan for $99.99. These plans likely unlock additional features or higher usage limits.

What devices is Privacy AI compatible with?

Privacy AI is designed for iPhone and iPad devices. Its interface is optimized for both, including features that leverage the unique form factors of devices like the iPhone Duo.

How often is Privacy AI updated?

The latest version of Privacy AI is 3.4.1, last updated on October 29, 2026. This indicates a consistent update schedule, suggesting ongoing development and improvements.