Drop in lectures, interviews, voice memos, and years of archived audio — get transcripts, local summaries, and a searchable library. No upload, no account, no cloud. Live meeting notes are Silo Meet's job.
Silo Systems builds infrastructure for people who would rather not negotiate with their own software. Silo Transcribe is the same discipline, pointed at one job (turning any recording into a searchable, summarized record) done entirely on the machine you already own. Your audio never becomes someone else's training data.
Capture, transcription, diarization, and summarization all run on your Mac through a bundled local runtime on your Apple Silicon GPU. The speech and language model weights download once from public open-weights mirrors, then Silo Transcribe works offline for the lifetime of the app, in a locked room exactly the way it works at your desk.
No analytics SDK, no telemetry, no account, no crash reporter. The Python inference layer binds strictly to loopback (127.0.0.1) as on-device IPC. It is not a network service. The audio you record and the transcripts it produces stay in your Application Support container, never transmitted anywhere.
Structured summaries, key points, action items, and speaker lists are generated locally by a Gemma instruction model through mlx-lm. The recording that would normally be fed to a cloud transcription service never touches a server. The intelligence is computed on hardware you already own.
Drop in the lecture you recorded, the interview on your phone, the voice memo from the car, or a folder of audio you have been meaning to deal with for years. When you need to capture something live, the menu bar records system audio and your microphone together — and for live meetings with cited action items, use Silo Meet.
A local Whisper model (large-v3-turbo, MLX) transcribes the audio on your Apple Silicon GPU, with in-memory 16kHz mono resampling for speed. Energy-based diarization splits the result into per-speaker utterances, so the transcript reads like the conversation actually happened, not one undifferentiated block.
A local Gemma instruction model, running through mlx-lm, reads the transcript and produces a structured summary, key points, action items, and the speakers, all written to a local SQLite store you can search with full-text FTS5. The summary a cloud service would charge you for, computed on your own machine and kept there.
Drop in a lecture, an interview, a voice memo, or years of archived audio — common formats import directly, and smart titles name each session for you.
Speech-to-text runs through a Metal-accelerated Whisper model (large-v3-turbo, MLX) with in-memory 16kHz mono resampling. Fast on Apple Silicon, and entirely on-device.
Energy-based partitioning splits the audio into clean per-speaker utterances, so the transcript reads like a conversation instead of a wall of text.
A local Gemma model via mlx-lm turns the transcript into a structured summary, key points, action items, and a speaker list, with no cloud service required.
Every session is indexed with SQLite FTS5, so you can query across months of recordings instantly and jump straight to the line that matters.
Correct the transcript inline, retitle sessions, and export transcripts and summaries to a folder you choose. Your words, your files, no re-upload.
Whisper and Gemma download once from public open-weights mirrors with live byte-progress. After that, every transcription and summary is offline.
Start a capture from the menu bar to record system audio and your microphone together. For live meeting notes with cited action items, the dedicated tool is Silo Meet.
System-wide ⌥⌘D dictation asks explicitly on first use: Apple Dictation, or the same local Whisper model the app already uses — no second download, no cloud, and never a silent engine switch. Repair or remove the model any time in Storage & Models.
Cloud services meter transcription by the minute and run your audio through their servers. Silo Transcribe is a single purchase, on your Mac, with unlimited local transcription and summarization, because it all runs on hardware you already own. Buy once, keep the record.
View on the App StoreSilo Transcribe is a private, on-device macOS app that turns any recording — lectures, interviews, voice memos, imported files, or live captures — into transcripts, local summaries, and a searchable archive on Apple Silicon. For live meeting notes with cited action items, the dedicated Silo app is Silo Meet.
No. Recording, transcription, and summarization all run on-device. Your audio, transcripts, and notes stay on your Mac — no account, no upload, no telemetry.
Otter.ai and Granola are cloud services that store your audio and transcripts on their servers, behind a subscription. Silo Transcribe keeps everything local for a one-time purchase, so confidential recordings never leave your machine.
Yes. Alongside file import, Silo Transcribe can record microphone and system audio directly through macOS. If your main job is live meetings — with summaries and action items cited to the transcript — Silo Meet is the dedicated tool.
Silo Transcribe is a one-time $14.99 purchase on the Mac App Store — no subscription and no per-minute transcription fees.
Yes. It runs on macOS 14 or later on an Apple Silicon Mac, using a Metal-accelerated Whisper model for fast on-device transcription.
Silo Transcribe is a one-time $14.99 purchase on the Mac App Store. No subscription, no account, no per-minute fees. Transcribe, summarize, and search entirely on your Apple Silicon Mac.
