The prospect hears a new name join before the rep says hello.

A discovery call is the first real impression a prospect gets of a company, and a named bot sitting on the roster before anyone has spoken — "Otter Notetaker joined the meeting" — is a small thing that some prospects shrug at and others read as a company that didn't ask before recording them. Either way, it's a detail a rep doesn't control once it's on the call.

Where the notes actually come from, either way

Otter and Fireflies solve the write-up problem by having that bot listen and transcribe from inside the call, and for a team that runs its whole pipeline through one of them, the CRM logging and call scoring are real capabilities this tool doesn't try to match. What comes with that is the recording, transcript and any call-scoring output sitting on that vendor's own servers, produced from audio the prospect never separately agreed to send there. Granola skips the bot on the roster but is the same kind of cloud service underneath, so the concern about where a prospect's words end up doesn't go away with it.

What the app does instead

Coii AudioNotes records the microphone and the system audio a Mac is already carrying, as two separate tracks, and transcribes both on that same machine while the call runs. A language model bundled inside the app turns the transcript into a summary once the call ends — decisions, action items, open questions — in time for the notes to go into whatever CRM the rep uses by hand, accurate rather than approximated from memory between calls.

Telling the rep's voice from the prospect's

A bot inside a call separates speakers using a per-participant feed the meeting platform hands it. Reading the Mac's own audio instead means that feed doesn't exist, so speaker separation works by voice print — matching each voice against the others already in the recording. A one-on-one discovery call is exactly the two distinct voices that matching handles most reliably.

What it deliberately doesn't do

There is no CRM integration and no automatic call scoring — nothing here logs a call against a deal record or grades a rep's talk-to-listen ratio on its own. There is no shared workspace a sales manager can browse without being sent the file directly; each recording lives on the Mac that made it, across up to three of a rep's own machines on one licence. It runs on macOS only, so a team on Windows laptops needs a different tool for the same job.

The objection that gets lost in a paraphrase

"They're worried about the price" is what survives in a CRM note typed after the call from memory. "We lost a EU customer last quarter because we couldn't invoice in euros" is what the prospect actually said, and it's the sentence that tells a sales engineer exactly what to build the next demo around. A transcript keeps the second version; a summary typed an hour later, after two more calls, tends to keep only the first.

A quarter of discovery calls, not just one

The value compounds across a pipeline. A rep three months in can search "multi-currency" or "EU entity" across every call that ever mentioned it, rather than trying to remember which prospect raised which objection — without any of those calls having passed through a server other reps' pipelines also sit on.

Who this genuinely isn't built for

A sales team that already runs its whole pipeline through a call- intelligence platform with shared coaching, deal scoring and CRM logging built in gets real value from that infrastructure — value this tool doesn't attempt to replace. This is built for the rep whose calls are mostly their own to record and log, not for a team whose forecasting depends on a shared call-scoring dashboard from day one.

The convenience of an automatic recorder, named honestly

A bot that joins every calendar invite automatically means a rep never has to remember to hit record before the prospect starts talking, which matters on a day with eight discovery calls and no gap between them. Switching to a tool that starts by hand puts that responsibility back on the rep — a real cost worth weighing, not a reason to pretend a manual recorder is free.

What a forecast conversation actually needs behind it

A sales manager reviewing a deal in a pipeline call wants more than a stage and a close date — they want to know what the prospect actually said about budget approval, and whether the objection raised in the notes was a real blocker or a rep's guess at one. A transcript settles that in seconds rather than needing the rep to reconstruct the conversation from memory in the review itself, which is usually the moment a shaky forecast gets caught or missed.

Starting on the calls that don't decide the quarter

The first couple of weeks go better started on routine calls — a check-in with an existing account, a low-stakes discovery call — rather than the one call that's actually going to close or lose a deal. A rep who tries the app on an ordinary week gets a feel for the write-up and where the recording sits on the desk, before relying on it for the call that decides whether the quarter lands.

What a sales manager can and can't see

A call's transcript lives on the rep's own Mac, not in a shared folder a manager can browse for every rep at once. If a manager wants to hear exactly how an objection was raised, the rep sends that specific transcript or summary — the same way they'd forward a quote in Slack — rather than a manager having standing access to a whole team's calls by default, most of which have nothing to do with the deal in question.

The version of this that fails quietly

The realistic risk isn't a leak — it's a rep who means to record every discovery call and simply forgets on the one call where the prospect says the thing that actually explains why the deal stalled. Nothing here reminds anyone to hit record before the call starts; building the habit on ordinary weeks, before it's the call that mattered, is the only real fix a tool can offer for a problem that isn't really about the tool.

Setting it up is smaller than the decision to switch

The first launch asks for two macOS permissions — microphone access and permission to record system audio — the same prompt any Mac app requesting audio capture triggers, and that's the whole of it. No account to register, no workspace to configure, no CRM to connect before the next call gets recorded. The larger part of moving off a bot-based habit is usually the habit itself: remembering to press record instead of trusting a bot that used to join on its own.

A discovery call from a trade-show floor

A call taken from a booth between sessions, or from a hotel room on whatever Wi-Fi a conference venue provides, is exactly the situation where a cloud notetaker's write-up depends on a connection that may not hold. Because transcription and the summary both run on the Mac itself, the notes get produced the same way regardless of the connection that day — a difference that shows up rarely and matters completely on the day a dropped connection would otherwise have meant no notes from a promising conversation.

What actually changes over a quarter of pipeline

Nothing about how a discovery call runs is different with this in the background — same platform, same questions, same conversation. What changes is what a rep has available at quarter-end, when a deal review asks exactly what a prospect said three calls ago and the answer depends on whether that call is a rough memory or an actual transcript, searchable on the Mac rather than reconstructed from a CRM note typed in a hurry.

What a deal review actually needs behind it

A sales manager questioning a stalled deal sometimes asks whether the objection in the CRM is the real one or a guess a rep typed in a hurry. A searchable archive of call transcripts turns that into an answerable question — what did the prospect actually say, at that point in the call — rather than a rep's recollection of how the conversation felt, which is exactly the kind of claim a forecast needs to survive being challenged in a pipeline review.

The question a prospect eventually asks

A prospect who asks where a recorded call goes deserves a straight answer, and "nowhere but the Mac that recorded it, and nothing is uploaded to produce the write-up" is one a rep can give without checking a vendor's privacy page first. It's also, for a prospect already wary of another vendor relationship, a more reassuring answer than most sales tools can offer about their own recordings — and one worth having ready before the question comes up rather than after.

The habit that outlasts any one tool

None of this replaces the judgment a good rep already brings to a call — reading hesitation, knowing when to push and when to back off. What it changes is whether that judgment is backed by an accurate record of what a prospect actually said, rather than a CRM note shaped by however the call was remembered an hour and two more calls later, after the specifics of one prospect have already started blurring into the next call on a busy pipeline day.

What it costs, what it runs on

Coii AudioNotes is $19, paid once, for three of a rep's own Macs, with a 30-day trial that needs no card and no account. It runs on macOS 13 Ventura or later, Apple Silicon or Intel. Against Otter's $8.33–$16.99-a-month Pro tier or Fireflies' comparable subscription, that's $19 total rather than a monthly cost multiplied across a whole sales floor; against Granola's $14-a-month Business tier the price gap narrows per seat, but the prospect's call still goes to a cloud service to produce the notes either way. Full comparisons here, here and here. A round-up of meeting notes apps without a bot and the wider case for a Mac-native meeting notes app and what an AI notetaker without the bot actually changes both cover ground this page doesn't repeat. The call that comes after the deal closes — a customer success handoff or a renewal check-in — is the same conversation from the other side of the relationship.