On-device recording of calls and rooms
Captures microphone input and, on Mac, system audio in separate lanes so it can record both sides of a call without a meeting bot.
Synopsule is a Mac and iPhone app that records and transcribes conversations locally, with optional on-device summaries and exports for sharing notes outside the app. It is built for users who want speaker-labeled transcripts without sending audio to the cloud.
Synopsule is a Mac and iPhone app for recording, transcribing, and optionally summarizing conversations on your device. It is designed to produce readable meeting notes with speaker labels, full audio kept for replay, and open text files that can be used outside the app.
The product emphasizes local processing: transcription runs on-device, raw audio is stored locally and deleted after finalization by default, and summaries are opt-in. On the Mac it can capture microphone input and system audio separately; on iPhone it records the room through the microphone for interviews, lectures, voice notes, and similar conversations.
Captures microphone input and, on Mac, system audio in separate lanes so it can record both sides of a call without a meeting bot.
Runs Whisper transcription entirely on your device, with a model bundled in the app and larger models available for download.
Separates voices, labels speakers, and recognizes returning voices on-device so names can carry across recordings.
Keeps the full audio on the device so you can replay any moment from the transcript, rather than discarding the source recording.
Creates opt-in summaries on-device, using Apple Intelligence or your own key, and only sends transcript text when summaries are requested.
Exports to Word, PDF, Markdown, HTML, SRT, and VTT, with one-tap sharing into Obsidian or Apple Notes.
Record a Zoom, Meet, or Teams call on Mac, capture the microphone and system audio separately, and review the labeled transcript with the original audio still available.
Use an iPhone to record interviews, lectures, hallway conversations, or voice notes, then keep a searchable transcript with time-anchored notes and flags.
Save recurring speakers once so they can be recognized in later recordings on the same device, reducing manual cleanup across future transcripts.
Export transcripts into formats that fit downstream editing or documentation workflows, including Markdown, Word, PDF, HTML, SRT, VTT, Obsidian, and Apple Notes.
It records conversations on your Mac or iPhone, transcribes them on-device, and can create optional summaries without sending audio off the device.
Synopsule supports Mac and iPhone. The page says one $1.99 purchase covers both devices.
No account is needed for the core workflow, and transcription works offline from the first launch.
Exports include Word, PDF, Markdown, HTML, SRT, and VTT, and the app can also share into Obsidian or Apple Notes.
Tactiq is an AI note taker for Google Meet, Zoom, and Microsoft Teams that transcribes meetings live and turns them into summaries, action items, and follow-up outputs. It is built around a Chrome extension and supports team workflows through sharing and integrations.
Scripta is a privacy-first AI notetaker that records, transcribes, and summarizes meetings directly on your device. The public site currently shows a Mac beta download and a Windows waitlist.
Speech to Text Converter is a browser-based transcription tool for live dictation and uploaded audio or video files. It offers a free tier for short tasks and a Pro plan for unlimited transcription, AI summaries, translation, speaker identification, and advanced exports.
Sanota is an app that turns spoken memories, reflections, and interviews into clear written stories. It supports personal storytelling, family history, and shared memories, with guided prompts and subscription pricing.
Carbon Voice is an asynchronous voice messaging app for teams and individuals, with transcripts, AI catch-up, and cross-device access. It helps people and agents communicate without needing a live call.
An OpenAI API guide for choosing the right speech architecture for live audio, translation, transcription, speech generation, and audio-capable chat. It helps developers map each speech application to the appropriate session type, endpoint, and connection method.