Speak, and Synapse turns what you say into an organized note with a title, a summary, key points and a list of action items. Everything happens on your iPhone: your voice is never sent to a server.
Built for people who handle sensitive information, like lawyers, doctors, journalists and executives, and for anyone who would rather keep their ideas in their pocket.
TRULY PRIVATE
• Transcription and AI run on your device. No servers, no cloud, no account.
• Works in Airplane Mode, on the subway or in the mountains.
• We collect no data: no analytics, no ads.
HOW IT WORKS
• Tap and talk: a quick idea or a whole meeting. You see the text as you speak.
• When you stop, your device's AI reads the whole transcript, however long: it adds a title, writes a summary, sorts the key points into sections and pulls out the action items.
• The note keeps what you said, word for word, split into paragraphs where you pause.
• Check off tasks, copy the note as Markdown or send it to Obsidian.
KNOWS WHO SAID WHAT
• Record a meeting or a conversation and each person gets their own turns in the note.
• Tap a name to rename it: the change reaches the title, the summary and the action items too.
IN 25 LANGUAGES
• Transcribes 25 European languages, including English, Spanish, French, German, Italian and Portuguese.
• It detects the language you speak, or you choose the language of the note.
TURN VOICE MESSAGES INTO NOTES
• Got a long voice message on WhatsApp or Telegram, or a recording in Files? Share it to Synapse and get a transcript, a summary and action items.
• On iPad, drag one or several audio files onto Synapse and each becomes a note.
• The audio is processed on your device and is never uploaded.
FOR EVERY MOMENT
• Apple Watch: capture an idea from your wrist.
• CarPlay: dictate an idea from your car's screen and see your recent notes.
• iPad: review and organize your notes on a bigger screen.
NO SIGN-UP
• No email, no password, no credit card.
• No note limit: only your device's storage.
UPFRONT ABOUT HOW IT WORKS
• On first launch, Synapse asks before downloading its speech models: Parakeet, an open speech recognition model based on NVIDIA's work, and a small model that tells speakers apart (about 800 MB in total). They download once; after that everything works offline.
• Titles, summaries and action items come from Apple Intelligence, built into the system. Synapse requires a device that supports Apple Intelligence (iPhone 15 Pro or later, or an iPad with Apple Intelligence) with Apple Intelligence turned on.
From a thought to an organized note, without anyone else reading it.
Show more
