CaptionNow 廣東話即時字幕・語音轉文字 vs Echosy

A real-time speech-to-text tool built around two things: accuracy and low latency. The developer is hard of hearing, and couldn't find a single app that handled Hong Kong Cantonese properly — the code-switching between Chinese and English, the technical terminology — while staying accurate and returning results instantly. So this one got built. Every decision in it comes from what actually holds up in daily use, not from a feature checklist. Features Live transcript — Text appears as you speak. No waiting for the sentence to finish. Captions for audio playing on your phone — Not just the microphone. Video calls, videos, and podcasts get transcribed too, which most comparable tools can't do. Floating captions — Picture-in-Picture keeps captions on screen while you use other apps. You pick the language; it doesn't guess — Mandarin (Taiwan / Mainland), Hong Kong Cantonese including Chinese-English code-switching, and English (US / UK / India / Hong Kong). Once you choose, it stays there — no drifting between languages mid-sentence. Offline recognition — Download a language pack on iOS 26 or later and it works without a network connection. Built for long reading sessions — No decorative clutter. Comfortable to watch through an entire lecture. Who it's for Deaf and hard-of-hearing users — Everyday communication support. See what's being said. Students — Live lecture notes, without losing the thread while you try to keep up. Professionals — Meeting minutes and interview transcripts, handled as they happen. Specifications This is transcription, not translation. What goes in is what comes out — with one exception: spoken Cantonese is transcribed into standard written Chinese, with English terms kept inline as spoken. Online mode uses a cloud recognition engine. Offline mode requires iOS 26 or later. Real examples of recognition errors are welcome — they're the most effective way to improve accuracy right now. Terms of Use (EULA): https://garnet-marimba-2dd.notion.site/Terms-of-Service-2d2f598ba98e80e5b065d198d8acf404?source=copy_link Privacy Policy: https://garnet-marimba-2dd.notion.site/Privacy-Policy-2d2f598ba98e80af99bae73136d3a3b9?source=copy_link

Stop taking notes. Start listening. Echosy records, transcribes, and summarizes your meetings, lectures, and interviews — so you can focus on the conversation instead of scribbling. Everything runs on your iPhone, using Apple Intelligence and on-device speech recognition. No cloud required. No subscription. No account. KEY FEATURES • On-device transcription in 60+ languages Powered by iOS 26's new continuous speech engine for English, Chinese (Simplified, Traditional, Cantonese, Hong Kong), Japanese, Korean, Spanish, French, German, Italian, Portuguese — with seamless long-form recording and no 60-second break points. Other languages use Apple's built-in speech framework, supporting Hindi, Thai, Dutch, Vietnamese, Arabic, Russian, and many more. • Automatic AI summaries The moment you stop recording, Echosy drafts a structured summary — overview, key points, decisions, action items — using Apple Intelligence on-device. No prompt engineering, no API juggling. Just tap record, speak, and read the summary. • Ask AI about your recordings Got a question about what was discussed? Open the chat drawer and ask. Echosy answers using the full transcript as context — completely offline. • Bring your own AI (optional) Prefer a cloud AI provider instead of the on-device engine? Echosy supports a range of services through a standard API endpoint — including DeepSeek, local Ollama servers, and any compatible provider you configure. Flip one switch in Settings and Echosy routes summaries and chat through your preferred service. • Fully private by default Audio never leaves your iPhone unless you explicitly enable a cloud provider. No account creation. No analytics on your voice. No training data. Just transcription. • Re-transcribe, edit, and export Saved recordings can be re-transcribed in a different language, edited inline, and exported as Markdown, plain text, or the native .echo bundle. • Beautiful, distraction-free interface Glass-morphism design, dark and light modes, onboarding that gets out of the way. LANGUAGES SUPPORTED English (US, UK, AU, CA, IE, IN, NZ, SG, ZA), Chinese (Simplified, Traditional, Hong Kong, Cantonese), Japanese, Korean, Spanish (Spain, Mexico, US, Chile), French (France, Canada, Belgium, Switzerland), German (Germany, Austria, Switzerland), Italian (Italy, Switzerland), Portuguese (Brazil, Portugal), Hindi, Thai, Dutch, Vietnamese, Indonesian, Malay, Turkish, Polish, Ukrainian, Swedish, Danish, Norwegian, Finnish, Czech, Slovak, Hungarian, Romanian, Croatian, Greek, Hebrew, Catalan, Arabic, Russian, and more. REQUIREMENTS • iPhone running iOS 17 or later • iOS 26 required for the new continuous transcription engine and on-device Apple Intelligence summaries • iOS 17–25 uses the classic speech recognition engine (still works, no downgrade) PRIVACY FIRST Echosy is designed so your voice never leaves your phone. No telemetry on your recordings. No cloud uploads unless you opt in. No sign-in. Delete the app and every trace is gone. Record better. Listen more. Let Echosy handle the rest.