Earshot Live Transcription vs OpenTranscribe

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

OpenTranscribe is a voice journal that runs entirely on your iPhone. You speak, it writes it down, and nothing leaves the device. Recording, transcription, and storage all happen locally. There is no account to create, no sync, no analytics, and no networking code in the app at all. It works the same in airplane mode, because being offline is not a setting here, it is how the app is built. Tap once and talk. A live transcript appears while you speak, and when you stop, the full recording is transcribed on the device. Finished entries land on a simple home screen, organized by day across the week. Each entry keeps its transcript and its recording, so you can read it back, play it, or transcribe it again later with a better engine. OpenTranscribe can also look back for you. When a day, week, or month ends, it can write a short reflection over the entries from that period, generated on the device by Apple Intelligence. Nothing about your journal leaves the phone to produce it, you choose which periods reflect and how the writing reads, and a quiet stretch is left quiet rather than invented. On iPhones without Apple Intelligence the feature simply stays out of the way. Your recordings are yours. Audio is kept on the device by default so an entry can be re-transcribed, and you can turn that off to have recordings deleted automatically once they are transcribed. Entries are stored encrypted on the phone. Transcripts can be edited in place, and every prior version is kept. A recording can also start without opening the app: from the lock screen, a widget, the Action button, Siri, or Shortcuts. And your journal can leave with you. Everything exports as Markdown, as Obsidian notes, or as a website that opens in any browser with a built-in player, and a sealed archive backs the whole journal up for a later restore. The archive is free for everyone, always, so your data never sits behind a paywall. The formatted exports are the first feature of the OpenTranscribe Club, a one-time purchase that supports the app, with more club features to come. The transcription engine is built to be swappable, and it must declare that it runs on the device. The app refuses any engine that does not, so audio can never be quietly sent off the phone. OpenTranscribe is open source and MIT licensed. A privacy claim cannot be proven by a policy, only by source you can read, so the code is public. You can check exactly what the app does and does not do at github.com/theiskaa/opentranscribe.