IntelligenceMesh vs FrankenTTS

IntelligenceMesh is an offline-first emergency companion built for the moments when infrastructure fails. Everything runs on your phone: no cloud login, no signal required, no data leaves the device unless you send it. On-device AI assistant Ask questions by voice or text. A small language model runs locally on your phone and answers with grounding pulled from verified emergency knowledge packs — first-aid, water safety, shelter guidance, disaster prep, kids' safety, and more. Every answer cites the source you can tap open. Offline knowledge packs Download curated guides from trusted authorities (CPR, Stop the Bleed, hypothermia, dehydration, evacuation, mechanical, medications, farm, legal, and more) before you need them. Every guide has a verifiable source URL so you can trust what the app is telling you. Offline maps + resources Cache tiles for your region and browse nearby shelters, hospitals, fire stations, police, pharmacies, water sources, food banks, fuel, and repair shops — sourced from OpenStreetMap and refreshed when you have signal. Deep-link straight to Maps or a tap-to-call. Live alerts, region-aware Pulls weather and disaster alerts from authoritative sources for your location (NWS in the US, MeteoAlarm across Europe, IMD in India, ECCC in Canada, PAGASA in the Philippines, INMET in Brazil, JMA in Japan, state services in Australia, GDACS worldwide). Only the providers relevant to where you are will run. SOS broadcast over the mesh Hold to send an emergency signal across a peer-to-peer mesh of other IntelligenceMesh users and paired hardware nodes — no cell tower needed. Includes your last-known location if available. Optional stick pairing Pair an IntelligenceMesh hardware stick over Bluetooth to add a physical button for voice asks, an on-body SOS button, and a low-power display for critical info even when your phone is off or dead. Privacy by design No email, phone, or location required to use core features. On-device encryption. No third-party trackers. Optional analytics can be turned off in Settings.

Give text a voice—entirely on your iPhone. FrankenTTS is a private, on-device text-to-speech and voice-cloning playground powered by a pure-Rust speech engine. After a one-time 1.86 GB model download, synthesis runs locally with no cloud inference. • Choose from built-in voices • Clone a voice from a short microphone recording, with a live level meter and automatic background-noise removal • Keep cloned voices in a private on-device voice library; rename, re-record, or delete them whenever you like • Share and import FrankenTTS voice cards—each carries a compact 4 KB voice fingerprint, never the original recording • Generate speech with an editable random seed • See the measured real-time factor for every run • View the waveform, play audio, and share compact M4A files • Turn generated speech into a branded MP4 video • Resume interrupted model downloads with SHA-256 verification Privacy is the default: entered text, microphone audio, voice fingerprints, imported pictures, and synthesized speech are not uploaded. Enrollment recordings are discarded after their on-device voice fingerprint is computed. Voice-card sharing and media export happen only when you explicitly choose them. Only clone or share voices you have the right and consent to use. A recent high-memory iPhone is strongly recommended.