Captionify vs Earshot Live Transcription

Captionify turns speech into text in real time, entirely on your device. Transcribe meetings, lectures, and conversations. Translate across languages instantly. No subscription. No account. Nothing sent to the cloud. REAL-TIME TRANSCRIPTION Using on-device AI, Captionify converts spoken words to text the moment they're said — no internet connection required. Ideal for lectures, meetings, interviews, and noisy environments where you can't afford to miss a word. LIVE TRANSLATION Understand any language as it's spoken. Captionify translates speech in real time so you can follow along in any conversation, anywhere in the world. FACE-TO-FACE CONVERSATION MODE Talking with someone who speaks a different language? Face-to-Face mode lets two people hold a natural bilingual conversation on a single device — one speaks, the other reads, then you swap. No interpreter. No awkward pauses. AGENT MODE Talk to an on-device AI assistant that can use tools, connect to your own MCP servers, and remember saved chats — all without sending anything to the cloud. CUSTOM PIPELINE (BETA) Mix and match independent transcription, translation, and voice engines — on-device or your own custom endpoint — to build a live pipeline that's entirely your own. AI SUMMARIES Powered by Apple Intelligence, Captionify distills long transcripts into the key points that matter. Everything runs on-device — your words never leave your phone. APPLE WATCH SUPPORT See live captions on your wrist and control recording remotely. Keep your phone in your pocket while staying connected to every word. SAVE & SEARCH YOUR TRANSCRIPTS Every session can be saved and searched later. Build a personal library of transcripts — no cloud storage, no account, no limits. PRIVACY BY DESIGN Captionify uses Apple's on-device AI for all processing. Your voice and your transcripts stay on your device always. 100% FREE No subscription. No paywall. No account required. Every feature, available from the moment you open the app.

Earshot is real-time, on-device captioning for iPhone - for conversations, lectures, doctor visits, anywhere you want to read what's being said. It's a free app that captions speech and ambient sound in real time, inspired by a Deaf researcher who'd spent his career on captioning. Having a disability shouldn't cost you money or your privacy. So I built Earshot. • Free — no sign-up, no sign-in, no ads, no upsells. • Private — everything runs on your device. The only network call is to download or update the local speech model so conversations never go to the cloud. • Offline — works with no Wi-Fi or cellular connection. • Multilingual — 99 languages, and it can translate any of them into English. • Ambient-sound aware — recognizes hundreds of environmental sounds, with full-screen alerts for urgent ones: smoke alarm, carbon monoxide, doorbell, crying baby, phone ringing, sirens. Accessibility tools shouldn't themselves be inaccessible. Free should mean free. Private should mean private. WHAT IT DOES • Real-time captions in a clean, focused screen, plus a chat-style "feed" layout. Tap the cog for text size, vibration, and ambient-sound options. • Translate non-English speech to English on the fly. • Full-screen urgent-sound alerts with strong haptics; ambient-sound tags shown in the corner when you want them. • Save transcripts on your device as readable documents. Star the ones to keep, filter by 1:1 or group, by alerts, by starred. • Share any transcript as plain text — it never leaves your device unless you send it. WHO IT'S FOR Built for the deaf and hard-of-hearing community as a private alternative to cloud captioning. Also useful in loud environments, for language learners, and for anyone who wants to read or save what was said. PRIVACY Audio never leaves your device. No accounts, no analytics, no ads, no tracking. The AI model downloads once on first launch (~244 MB) — the only network request the app makes. Full policy at briankemler.github.io/LiveTranscribe/privacy. REQUIREMENTS iPhone on iOS 17 or later. Works offline after the one-time model download. CONTACT brian.kemler@gmail.com