Five tools win five jobs. One wins a different axis.

“Best AI notetaker” has no single answer, because the leading tools are optimized for different jobs. Fathom wins on free tier, Fireflies on sales ops, Otter on real-time archive, tl;dv on video, Granola on clean bot-free notes. Each is genuinely the best at its job. This roundup concedes that first — and then asks the one question none of them answer the way Fazit does.

The honest scorecard

Every tool here produces a clean summary, action items, and a follow-up draft in 2026 — that race is over. So the useful table is not “which summarizes best,” it is “what is each one actually built for, and where does the audio go to get there.”

              BEST KNOWN FOR         A BOT?     AUDIO STAYS
                                                ON DEVICE?
Fathom        Generous free tier     yes*       no
Otter         Real-time + archive    yes        no
Fireflies     Sales / CRM ops        yes        no
tl;dv         Video + EU flag        yes        no
Granola       Clean bot-free notes   no         no
Fazit         Never recording        no         yes

* Fathom is rolling out a botless capture mode; historically it joined as a visible bot, and its recording still lands in the cloud either way.

Five tools win a category in column one. Only the last row answers no in the final column. That gap is the whole article — everything above the Fazit row competes on features and deletion promises; the Fazit row competes on whether a recording exists at all.

Fathom — best free tier

Its real strength. A genuinely generous free plan, a polished experience across Zoom, Meet, and Teams, and enterprise trappings — SOC 2 Type II, HIPAA, SSO. If you want a capable notetaker at zero cost, this is the honest pick, and it is cross-platform where Fazit is Apple Silicon only.

The recording weakness. The recording lands in Fathom’s cloud, and its policy permits using de-identified customer data to improve its own models unless you find the opt-out. As of April 2026 Fathom was acquired by QuestionPro — meaning the corpus of everything it ever recorded changed corporate ownership through an M&A transaction. That is not a hypothetical “what if the vendor changes”; it already happened.

Where Fazit wins decisively. There is no server-side recording to inherit. Nothing was stored, so nothing changes hands when the cap table does.

Otter — best real-time archive

Its real strength. Fast real-time transcription, a searchable company-wide archive, a long track record, and aggressive pricing. If meeting notes are a shared knowledge base for the whole org, Otter has scale on its side.

The recording weakness. Otter is the defendant in a federal class action (Brewer v. Otter.ai) alleging it recorded conversations without all-party consent and trained its speech models on user recordings; its policy describes training on “de-identified” recordings. A motion to dismiss was argued in May 2026 and is under submission. It is simply the litigated version of the risk the whole cloud category carries.

Where Fazit wins decisively. You cannot train a model on a recording that was never created. Fazit’s audio lives in a RAM ring buffer and is consumed by an on-device model — no recording to subpoena, leak, or feed to a training set, and a one-line consent disclosure ships with the app.

Fireflies — best for sales ops

Its real strength. The deepest integration ecosystem here — CRM field sync, Slack, unlimited-transcription tiers, conversation analytics — which makes it sticky for revenue teams that want pipeline automation, not just notes.

The recording weakness. Fireflies faces biometric-privacy litigation in Illinois (including Cruz v. Fireflies.AI Corp., filed December 2025) alleging voiceprint collection without consent, and its recording bot is now flagged by Google Meet as a third-party security risk that can be blocked from joining. A centralized store of voiceprints is precisely the asset BIPA statutes were written to govern.

Where Fazit wins decisively. No voiceprint is extracted, no bot needs to be admitted (or gets flagged), and there is no central store of meeting data to access — because there is no central store.

tl;dv — best for video

Its real strength. Strong recording and playback UX, coaching and conversation analytics, and EU-headquartered positioning that reads well to European buyers who want video artifacts of their calls.

The recording weakness. A video recording is more data than an audio one, not less — and it is still a visible-bot cloud recorder. Free-tier recordings auto-delete after three months (a retention limit, not a privacy guarantee), and despite the EU branding it is described as still working toward full GDPR compliance. Cloud recording under an EU flag is still cloud recording.

Where Fazit wins decisively. For a European regulated professional, a pipeline that transcribes in volatile memory and never writes an audio file to a sound carrier is a materially stronger position than a promise of compliant storage — “never created” and “created then deleted” are different legal facts under German law (§201 StGB). That argument is in Why “Never Records” Is Not Marketing.

Granola — best notes, and the only real comparison

Its real strength. Granola is the one tool that shares Fazit’s instinct: no bot in the room, capture the audio your own device already hears, and don’t retain it. It is SOC 2 Type II, the notes are excellent, and on privacy it is genuinely better than every bot-based tool above. If Fazit did not exist, Granola would be the right answer.

The recording weakness. Granola is bot-free, but it is not on-device transcription. To turn audio into text, it streams your call to third-party services — Deepgram, AssemblyAI, OpenAI, Anthropic — and deletes the raw audio after transcription. Your conversation still transits the public internet to four subprocessors. Deletion is a promise about what happens after the audio arrives on someone else’s server — not a guarantee that it never arrived.

Where Fazit wins decisively. Fazit’s speech model runs on the device. Audio is captured into a fixed-size RAM ring buffer, a local model consumes a snapshot, and the note is written to your vault as Markdown. The audio never leaves the machine — so there is no subprocessor to list, no transfer mechanism to disclose, and no “deleted after transcription” step to trust, because there is no transcription server to delete it from.

So which is best?

It depends entirely on the job — which is the honest answer, not a hedge:

• Want a capable notetaker for free? Fathom.
• Need a shared, searchable team archive? Otter.
• Living in a CRM and want pipeline automation? Fireflies.
• Want video recordings of your calls? tl;dv.
• Want the cleanest bot-free notes? Granola.
• Doing regulated, privileged, or confidential work where the recording is itself the liability? Fazit — because it is the only tool where the recording never exists.

That last row is not a sixth feature competing with the other five. It is a different axis. Every note Fazit writes carries audio_retained: false in its frontmatter — not a compliance checkbox, but a description of the execution path, true because there is no code path that writes audio to disk.

What Fazit gives up (so you don’t find out later)

The on-device design is a trade, and it is worth naming the costs before you choose:

• Apple Silicon only. The pipeline runs on the Mac’s neural hardware. If your team is on Windows, Fazit is not for you today — Fathom or tl;dv are.
• No bot means no proxy attendance. A cloud bot can join and record a call you are not on. Fazit only captures what your own machine hears. If your workflow depends on recording meetings you don’t attend, that is exactly what Fazit refuses to do.
• A smaller integration surface than Fireflies or Otter. Fazit writes Markdown into your vault; it is not a CRM autopilot.

Those are deliberate. The moment a tool records calls you didn’t attend, or buffers to a server for reliability, it inherits the exact risk this roundup is about. Fazit declines the features that would require it.