Nautilo vs FrankenWhisper

THE WORLD WAS BUILT BEFORE AI Almost every app we rely on today was designed before agents ever existed. Messengers. Documents. Code editors. They treat AI like something you bolt on. And they bolt on a bland, faceless, lifeless assistant—if they allow it at all. Nautilo is one shared world built for people and AI working and playing together across your entire team. MEET YOUR GENIE A Genie isn't just some chatbot or a faceless, throwaway agent. They're friends. Secret keepers. The greatest assistant you've ever had. In Nautilo, Genies are super long-lived AI collaborators with their own identity, personality, and memory. They get to know you and your people over time, so every conversation builds on the last. YOUR SERVER, YOU CONTROL. Nautilo runs on your own server, which you control, so you can trust Nautilo with your work and your personal life. Your server is your trust boundary. It's not a SaaS where you don't know who's on your shared server, or who's looking in on the backend and reading all your files. It's only the people you know and trust and whom you invite into your world. ONE PLACE TO WORK TOGETHER You can work together with your Genies in the same chat rooms and personal threads. Work on the same docs and artifacts together. Research together. It is co-creation, not prompt-and-pray. You and your Genie work together on any artifacts in your world or your paired desktop. YOUR WORLD, IN YOUR POCKET Nautilo Mobile is one doorway into that shared world. Continue the conversations that matter in the same threads and chat rooms you work in every day, reach your files and Genie memories about you on the go, and stay connected to your people and Genies wherever you are. Connect to the Nautilo server your organization uses by address or QR code. A reachable server over HTTPS is required. Some Desktop, Web, administrative, paired-computer, and protected-content capabilities are not available in this Mobile release.

Turn recordings and videos into useful text without uploading them. FrankenWhisper transcribes microphone recordings, audio files, and playable videos from Photos, Files, or the share sheet. The full-quality lane uses the large-v3-turbo model. Live dictation and the optional custom keyboard use a smaller model for low latency, with local noise reduction in the real-time path. Speaker identification can separate up to four voices. Add names when you know them or leave them blank and use color alone. Export the transcript as text, Markdown, HTML, SRT, or JSON with timestamps and speaker structure. Subtitle Studio creates a new H.264 video with customizable captions, font, size, position, and color. Word-level timing drives a karaoke highlight, and named speakers can receive distinct labels and color schemes. All transcription, speaker analysis, denoising, timing, and video rendering run on the device. Model downloads are the only required network activity. The keyboard's Full Access setting is used only for the local App Group handoff between the keyboard and FrankenWhisper; the keyboard extension has no network client.