Privacy AI: Agent & Chatbot

About Privacy AI: Agent & Chatbot

Ratings & reviews

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.

App privacy

The developer, AcmeUp Inc., reported these privacy practices to Apple.