Privacy-first meeting AI · macOS & iOS

Your meetings
never leave your Mac.

Synogram records, transcribes, and summarizes meetings using your own OpenAI key — locally on your device. No subscription. Nobody in the middle holding your audio.

Download for Mac

macOS 14.4+ · iOS 17.0+ · Bring your OpenAI or OpenRouter key

Audio stays on device No vendor lock-in No subscription Cancel nothing
Synogram — Q3 Roadmap Sync
Local · your key gpt-4o-transcribe

Q3 Roadmap Sync

Tue · 38 min · 3 speakers · English
Summary

The team aligned on three priorities for Q3: shipping the BYOK flow, cutting transcription latency for sessions over 30 minutes, and opening Mac TestFlight to a wider cohort.

Action items
  • Draft BYOK onboarding copy — Mai
  • Profile transcription on 60-min recording — Ken
  • Open TestFlight to next 50 sign-ups — Ranatchai
Transcript

Mai 00:12 — Should we ship the BYOK toggle this sprint or wait until cloud auth is GA?

Ken 00:18 — Ship it this sprint. Cloud is a strict superset; we don't gain anything by waiting.

Ranatchai 00:24 — Agreed. Privacy story is sharper if BYOK lands first.

Above: Synogram on macOS · simulated meeting

01 · The problem

You're paying $20 a month to summarize your own meetings.

Otter, Fathom, Granola — month after month after month. And while the bill is annoying, the deeper cost is harder to see: every call you've ever recorded is now sitting on someone else's server, indexed against terms you didn't read.

You don't need another SaaS. You need the audio to stay where it was recorded — on your Mac, your iPhone — and the AI to do its work without anyone in the middle.

Otter · $16.99–30/mo Fathom · $24/seat/mo Granola · $18/mo Fireflies, Read.ai, …
02 · The shift

Synogram flips the model.

Your Mac records. Your key transcribes. Your key summarizes. Nothing sits in the middle.

03 · How it works

Three steps. Zero middleman.

step 01 on device

Record

Mac captures both your mic and system audio — Zoom, Meet, Teams, anything playing. iPhone records the room. Audio is written straight to a local file. Nothing leaves your device yet.

recording.caf · written locally

step 02 your key

Transcribe

The audio chunks are sent directly from your laptop to OpenAI using your API key. Speakers are diarized, timestamps attached, language auto-detected — Thai, Japanese, English, more.

A · 00:12 Should we ship BYOK this sprint?

B · 00:18 Yes — cloud is a strict superset.

step 03 your key

Summarize

Pick a template — Standup, UX Research, Sales, Discovery, Retro, or General — and the transcript becomes a structured summary with action items, decisions, and per-speaker notes.

action items

— Profile transcription on 60-min recording (Ken)

— Open TestFlight to next 50 sign-ups (Ranatchai)

No Synogram middleman

In BYOK mode, your laptop talks directly to OpenAI. Synogram has no proxy, no server, no logs, no copy of your audio. We literally cannot read your meetings — we don't run anything that touches them.

04 · Privacy & local-first

Built for people who treat their meetings like their email.

Most meeting tools were designed cloud-first — you upload your audio, they do the work, they keep a copy. Synogram is designed the other way around: local-first, with the cloud as an optional convenience you control.

Local SQLite, on your disk

Every meeting — audio, transcript, summary, your notes, your task progress — lives in a local SQLite database (GRDB) inside the app's sandbox. Back it up to Time Machine. Move it to a new Mac. Delete a recording and it's gone for real.

API keys in the system Keychain

Your OpenAI and OpenRouter keys are stored in the platform Keychain — Secure Enclave-backed on iPhone, the same place Safari keeps your saved passwords on Mac. They never appear in plaintext on disk and never reach Synogram's servers (we don't have any in BYOK mode).

Direct connection to your AI provider

When transcription runs, the audio chunk goes straight to api.openai.com over TLS, authenticated with your key. Synogram doesn't proxy it, doesn't log it, doesn't see it. The network trace shows two endpoints: your machine and OpenAI's.

Cloud is opt-in, not on by default

If you want billing convenience instead of managing API keys, you can sign in to Synogram Cloud — but you have to choose it. The app ships in BYOK mode. No background sync. No "anonymized telemetry." No surprise upload.

05 · Summaries that match the conversation

Six templates. One for every kind of meeting you actually have.

Each template is purpose-built — different headings, different angles, different signals to pull out. Outputs stay in the original language, no translation.

general

General Meeting

Executive summary, decisions, action items, per-attendee notes. The safe default when you're not sure which template fits.

standup

Standup

Yesterday / Today / Blockers per person. Plus risks, decisions, and a clean action item list — what daily standup notes should always look like.

ux research

UX Research

Participant snapshot, insights, pain points, verbatim quotes, validated hypotheses, surprises, and follow-up questions.

sales

Sales Call

Account snapshot, pain points, use cases, objections, buying signals, decision process, pricing notes, next steps.

discovery

Customer Discovery

Who they are, job-to-be-done, current workflow, what works, friction, workarounds, tools in play, opportunities, open questions.

retro

Retrospective

TL;DR, what went well, what didn't, lessons, action items, experiments to try next sprint. Per-speaker notes preserved.

Not the right shape? Open the summary, ask a follow-up question in plain language, and Synogram refines it grounded in the transcript — same key, same privacy posture.

Beyond record + summarize

Tools your meeting AI should give you.

You picked the key. Pick the model, the prompt, the speaker names. Synogram gets out of the way.

Q3 Roadmap Sync — Summary
Summary · v2

Decisions & next steps

Re-summarize with
OpenAI · gpt-4o-mini
fast · ~$0.02
current
v2 stays. New version appears alongside.
Action items
  • Ship the BYOK toggle this sprint, cloud as strict superset
  • Profile transcription on 60-min recording
  • Open Mac TestFlight to next 50 sign-ups
01 · Model choice

Pick the brain. Resummarize anytime.

You're paying OpenAI directly. Use any model worth the tokens — and switch when a sharper one ships next month, without losing the version that's already in your notes.

  • OpenAI, Anthropic, Google, anything via OpenRouter
  • One click resummarizes; the original stays
  • Same key. Same privacy posture. Different brain.
02 · Ask the meeting

Talk to the transcript. Not at it.

Ask questions in plain language and Synogram answers from this meeting — grounded in the actual transcript and summary, with line-level citations you can click into.

  • Cites the timestamp it pulled the answer from
  • Speaks the meeting's original language
  • Same key, no separate "AI assistant" bill
Ask — Q3 Roadmap Sync
Who flagged the 60-minute transcription issue, and when?
R
S
Synogram · grounded
Ken raised it at 00:18 — he said 60-minute recordings were taking too long to transcribe and blocking review. Mai agreed and added it to the action items.
00:18 transcript Action items
What's the deadline?
R
S
⌘ ↵
Q3 Roadmap Sync — Summary
v3 · just now edited with prompt

Sprint priorities, ordered by owner

Mai — Ship BYOK toggle this sprint. Cloud is a strict superset.

Ken — Profile transcription on a 60-min recording; target sub-30s per 10 min.

Ranatchai — Open Mac TestFlight to next 50 sign-ups.

Edit with AI

"Make it shorter. Group action items by owner. Cut the preamble."

applied to v2 → v3
History
v3 · now
+ prompt edit
v2 · 3m ago
gpt-4o resum.
v1 · 12m ago
gpt-4o-mini
03 · Refine with a prompt

Re-shape the summary in one sentence. Roll back if you don't like it.

Tell Synogram what to change in plain language — "shorter," "group by owner," "drop the preamble," "in Thai" — and it rewrites the summary. Every version is saved. Revert without losing your work.

  • Natural-language edit prompts, no template lock-in
  • Full version history, one click to revert
  • Diff every change against the previous version
04 · Speakers

Auto-diarized. Tag once. Across every line.

OpenAI's diarization model splits voices automatically. Tag a speaker once — Mai, Ken, Ranatchai — and Synogram retroactively colors every line they said, in any language the model heard.

  • Speaker auto-split with timestamps
  • One-click tag re-labels every line at once
  • Works in Thai, Japanese, English, mixed — original language preserved
Transcript — Sprint kickoff (TH)
3 speakers th-TH auto-diarized
42:18
M
มาย (was Speaker A) 00:12

ลุยเลยมั้ย — เราจะ ship BYOK toggle ทันสปรินต์นี้ไหม?

?
Speaker B 00:18

ลุยเลยครับ — Cloud เป็น superset อยู่แล้ว ไม่ได้เพิ่ม risk อะไร

Tag Speaker B as

Applies to all 47 lines from Speaker B in this meeting.

R
Ranatchai 00:24

เห็นด้วย — privacy story จะ sharp ขึ้นถ้า BYOK land ก่อน

06 · Built for Apple platforms

Not an Electron wrapper. A real Mac and iPhone app.

macOS 14.4+ Sonoma · Sequoia

Mic + system audio, captured cleanly

ScreenCaptureKit pulls your microphone and the system audio coming from Zoom, Meet, Teams, FaceTime, anything playing — without screen recording, without a virtual driver, without a kext.

  • Menu-bar resident, out of your way
  • Floating pill window for record / stop
  • Markdown-rendered summaries with live task checkboxes
  • Native copy / share sheet support
iOS 17.0+ iPhone · TestFlight

Lock the phone. Keep recording.

Background audio mode means the recording continues whether the phone is locked, in your pocket, or you've jumped into another app — and a Live Activity on the Lock Screen lets you stop with one tap.

  • Background recording, jetsam-resilient .caf format
  • Lock Screen Live Activity with stop control
  • Real-time waveform + level meters during recording
  • Native share sheet, system Markdown viewer
07 · The math

And — yes — it's also cheaper.

Honest numbers. You pay OpenAI directly for the transcription and summarization tokens you actually use. Synogram charges nothing in BYOK mode — there's no per-seat fee, no recurring bill, nothing to cancel.

BYOK your key

Synogram

Pay OpenAI for usage. Nothing to Synogram.

~$0.40 per recorded hour (estimate)
  • No subscription
  • No per-seat fee
  • Unlimited recordings
  • Switch models any time (OpenAI / OpenRouter)

Estimate: gpt-4o-transcribe at $0.006/min · ~$0.36/hr audio · plus a few cents per summary. Your actual cost depends on length and model choice.

Subscription your audio on their server

Otter · Fathom · Granola

Monthly fee. Their AI. Their cloud.

$18–30 per month (per seat)
  • ·Pay even in months you don't record
  • ·Audio stored on their cloud, indefinitely
  • ·Caps on minutes / recordings on most tiers
  • ·Switching tools means losing your archive

Pricing as of mid-2025 from each vendor's site. Annual plans roughly 20% lower; per-seat for teams.

Optional

Don't want to manage API keys?

Synogram Cloud is a single magic-link sign-in. We route your transcription and summarization through Vercel AI Gateway and bill you for what you use — no monthly subscription, no per-seat fee. Same privacy stance: zero data retention on the gateway, and you can switch back to BYOK any time.

08 · Frequently asked

Questions, answered honestly.

What API keys do I need?
One OpenAI key for transcription (the diarization model is OpenAI-only today). Optionally an OpenRouter key for summarization if you want to use Claude, Gemini, or any other model. You can paste both during onboarding and switch between them per-meeting.
What does a meeting actually cost?
Roughly $0.006/min for transcription with gpt-4o-transcribe-diarize, plus a few cents per summary depending on model and length. A typical 30-minute call costs around $0.20 end-to-end. A full-hour deep-dive is closer to $0.40–0.60. You pay OpenAI directly.
Which languages does transcription support?
Whatever OpenAI's model supports — English, Japanese, Thai, Chinese, Korean, most European languages. Language is auto-detected; you can also hint it. Summaries stay in the conversation's original language (no surprise translation).
Does it work offline?
Recording works offline — audio is written straight to a local file. Transcription and summarization need internet because they call OpenAI. When you're back online, you can process anything in your queue.
Where exactly does my data live?
On your device, in the app's sandboxed data folder, inside a local SQLite database (GRDB). Audio files sit next to it. API keys are in the platform Keychain. Nothing leaves your machine except the transcription/summarization requests you explicitly trigger — and those go straight to OpenAI in BYOK mode.
Mac + iPhone — does my data sync?
Not yet — each device keeps its own local database. We'd rather ship sync correctly later than ship a leaky version now. If you want a single place for everything, Synogram Cloud syncs across devices behind your account.
What if I cancel my OpenAI account or run out of credit?
Synogram still works — you can record offline, keep your local archive, and switch to a different provider (OpenRouter for summarization, another transcription provider as support lands) without losing anything. The app doesn't lock you in.

Get your meetings back.

Off the SaaS treadmill. Off someone else's server. Onto your Mac, where they always should have been.

Download for Mac

No signup · No subscription · Your key, your data

iOS · TestFlight beta

Join the iPhone beta

Synogram for iPhone is in private TestFlight beta — we add testers in small batches to keep the experience tight. Drop your email and we'll send an invite as soon as a slot opens.

We only email the invite. No newsletter. No marketing.