Best Free AI Note-takers

Fireflies sends a recorder into the meeting and gets out of the way. It can be invited to a single call or set to join everything on your calendar, and once it is running the output lands wherever you have pointed it — a chat channel, a CRM record, or another system through the API.

What makes it worth a close look is where the paywall sits. Unlimited transcription, unlimited summaries, live notes, meeting search, the assistant that answers questions about past calls, and API access are all on the free plan. The cap is storage rather than usage: four hundred minutes of recordings for the whole team, after which older meetings have to be deleted to make room. Paid tiers raise that and add integrations, conversation analytics and administrative controls.

The thing to weigh is what happens to the data afterwards. The vendor states that meeting data never feeds AI model training and describes a zero-day retention arrangement with its own vendors. It holds SOC 2 Type II and GDPR, and HIPAA with a business associate agreement on the enterprise tier. Custom data retention is an advanced-tier control rather than a default.

Fathom's pitch is that the free plan is not a trial. Unlimited recordings, unlimited storage and unlimited transcription in thirty-eight languages are all included without payment, and the vendor says explicitly that you are under no obligation to upgrade when the premium preview ends. What the free plan does limit is the advanced summaries: five calls a month, after which you get the general template.

The capture choice is the other thing worth knowing. Fathom can send a bot into the call or record without one, with the bot-free mode currently marked as being in beta. That flexibility matters because the two approaches fail differently — a bot is visible to everyone in the room, and device capture depends on the machine you are sitting at.

The catch is that the intelligence, not the recording, is what the free plan meters. Paid tiers add advanced summaries without a monthly cap, a conversational assistant, and on the business tier a CRM sync that updates records after meetings rather than simply linking back to them. Highlights can be pushed into a chat channel as the meeting happens. Mandarin is absent from the language list despite the count of thirty-eight.

Granola is a desktop application rather than a meeting participant. You open it, press start, and type whatever you would have typed anyway; it listens to your microphone and your computer's audio at the same time and keeps a transcript alongside your notes. When the call ends it writes a summary from both, which is a different product from one that summarises a recording you never looked at.

The trade-off is stated plainly by the vendor: it will not join or record anything on its own. That costs you the meetings you forget to start it for, and buys you a tool that never appears in someone else's participant list. For a lot of people that is the whole argument, and it is why the free plan is worth taking seriously — it carries chat across your past meetings alongside custom note templates, a pairing most vendors hold back.

The cost is real, and it is about data rather than features. Everything is stored on AWS in the United States with no regional option, notes and transcripts are kept indefinitely unless an administrator configures otherwise, and anonymised data is used for training until you turn that off in settings. Audio itself is deleted once transcription finishes.

tl;dv is built in Europe and it shows in the choices it offers. The security page states that customers can choose whether their AI is hosted in Europe or the United States, that the company is GDPR-compliant for all users, and that no customer data is used to train the AI models it works with. Those three together answer most of what a procurement review asks about privacy before it is asked.

The product itself is organised around clips. Rather than producing one summary and leaving you to scroll a transcript, it is designed for cutting the useful ninety seconds out of an hour and passing it on. That suits recruiting, user research and sales review more than it suits a weekly team call.

The catch is disclosure rather than capability. The free plan carries unlimited transcription in over thirty languages, with recordings deleted after three months. Paid tiers add custom note templates, search across the whole transcript archive, an API with webhooks and an MCP server, and CRM field mapping. The language count is advertised rather than enumerated: the vendor's own language page reads as marketing, offering coverage "from Portuguese to Mexican", and Mexican is not a language.

MeetGeek does not make you pick a capture philosophy. The free plan lists recording through a joined meeting and no-bot recording through a browser extension and desktop app, which means the choice can be made per meeting rather than at purchase. That flexibility is rarer than the marketing in this category suggests.

The free tier is genuinely capable: three hours of transcription a month, transcription in over a hundred languages with a published per-language table, unlimited summaries, global search with AI chat, and API and MCP access. Storage is where it bites, with transcripts kept three months and audio one. Paid tiers raise the hours and storage and add meeting templates.

The thing to weigh is the default posture. The recorder joins meetings on its own, and the documented control is a rule for excluding meetings rather than a switch for including them — which tells you the default posture. On security the company holds SOC 2 Type II and hosts on Amazon infrastructure. Automatic language detection, useful if your meetings are not all in one language, is reserved for paid users.

Bluedot records without putting a participant in your meeting, and leads with privacy in its own marketing. That combination is becoming less rare, but the way it draws its pricing tiers still is.

Bluedot draws its tiers the other way round from the usual arrangement. Slack, Notion, Zapier and Make connections are on the free plan, while custom note templates wait until Pro and CRM and applicant-tracking integrations until Business. If your bottleneck is getting notes in front of a team rather than shaping how they read, that is the more useful way round.

Webhook access starts on the Basic tier, with organisation-wide webhooks and MCP on Business. The catch is silence on languages: Bluedot names no transcription list anywhere public, so its coverage is unrecorded here and the language filters pass it by. For a team working in English with a Slack habit and a dislike of meeting bots, it is a comfortable fit; anyone who needs a specific language should ask first.

Tactiq works as a browser extension rather than a participant or an application. It reads the live captions your meeting platform is already producing, which is why the transcript appears in real time and why nothing shows up in the participant list. It also explains the product's most unusual piece of documentation.

Because it depends on the platform's own speech recognition, what Tactiq can transcribe varies by where you are meeting. The vendor publishes a separate language list for Google Meet, Microsoft Teams and Zoom rather than one list for the product. That is more honest than a single headline number, and it is worth checking the list for the platform your team actually uses rather than the aggregate.

The cost is volume and dependence. The free plan allows ten transcripts a month with five AI credits, which makes it a genuine trial rather than a running tool. Pro lifts transcripts to unlimited, team tiers add sharing and centralised administration, and data retention controls arrive on Business. A HubSpot connection is documented as a self-serve setup with no plan requirement stated.

Otter has been doing this longer than almost anything else in the category, and it shows in the parts that are hard to rush: the live transcript is genuinely usable while a meeting is running, speaker identification is on the free plan, and chat that reaches across past meetings is too.

Two things deserve care before choosing it. The first is languages. Otter transcribes English, Spanish, French, German, Japanese and Chinese, and nothing else — its help centre answers a direct question about Portuguese with a flat no. For a team that meets in one of those six that is irrelevant; for anyone else it rules the product out entirely, and the figure is easy to miss because the marketing does not lead with it.

The thing to weigh is training. The vendor states that it de-identifies user data before using it to train its own models, while separately confirming that its AI service providers do not train on customer content. Both statements are true and they answer different questions. Retention is a thirty-day trash bin rather than a configurable policy, and the API arrives only on the enterprise tier.

Read AI produces a meeting report rather than a set of notes. Alongside the transcript and summary it measures engagement and sentiment, breaks the dialogue out by speaker, and shows an in-meeting dashboard while the call is still running. Whether that is insight or noise depends entirely on what you are trying to do with it.

Coverage is a strength. Twenty-six languages are enumerated for meeting reports, and in-person meetings, live events and mobile capture are all documented rather than implied. The one documented limit is mixed-language meetings, which the vendor says are not fully supported and may produce inconsistent results.

The thing to weigh is location. On privacy it sits in the middle, honestly documented. Data is stored encrypted in an Amazon data centre in Northern Virginia, with other locations available only by arrangement through the sales team. Retention is genuinely in the user's hands: you choose whether audio and video are saved for playback, and if you decline, nothing beyond what is needed to produce the report is retained. Premium integrations covering Salesforce, HubSpot and webhooks sit on a paid tier.

Grain is aimed at teams who go back over their calls — sales coaching, customer research, anything where the recording gets watched rather than filed. The free plan carries the AI notepad with live notes, a running transcript and clip creation, which is the part of the product people actually use day to day.

Integrations are where the tiers bite. Slack delivery, a personal Zapier connection and a personal API arrive on the starter tier; HubSpot and Salesforce, workspace-level Zapier and a workspace API wait until business. That is a conventional ladder, and worth mapping against how many people will actually need the CRM connection.

The cost is not the product but what you can find out about it. Documentation is the weak point rather than the product. Grain holds a SOC 2 Type II report, released through a trust centre request rather than published, and hosts all of its software in Amazon facilities in the United States. Its support centre refuses anonymous readers entirely, so the language question could not be answered at all — an absence of access rather than of capability.

Fellow treats a meeting as something with a beginning rather than only a recording. Agendas, notes and follow-ups sit in one place, and the AI recap is attached to a structure rather than produced in isolation. For recurring meetings — one-to-ones, team syncs, anything with continuity — that changes what the notes are for.

Templates are a real part of the product: purpose-built AI note templates for one-to-ones, sales calls, project syncs, interviews and all-hands, with custom templates you can author yourself. Organisation-wide templates arrive on the business tier, along with multi-calendar sync on enterprise.

The privacy position is stated plainly: Fellow never trains its AI on customer data, and offers granular recording policies for controlling what is captured and when. The cost is a gap in disclosure: no transcription language list exists publicly, leaving coverage unrecorded and the entry outside the language filters. For an English-speaking team that is immaterial; for anyone else it is worth asking before committing.

Jamie's proposition is narrow and clearly stated: no bot joins your call, storage and processing are resident in the European Union, and customer content stays out of model training. For a European team with a procurement checklist, that combination answers most of the questions before they are asked.

Because it captures device audio rather than joining as a participant, it works for in-person conversations as well as online ones, and it does not depend on which meeting platform your counterpart happens to use. Meeting audio is deleted once transcription finishes, so what persists is the text.

The cost is documentation rather than capability. The documentation is the weak spot. Language coverage is advertised as over a hundred for notes and ninety-nine or more for summaries — two different figures on the same page — and no itemised list exists on any page that could be read, which leaves the filters empty for it. The documentation site refused three separate fetch attempts. Salesforce, HubSpot and similar connections arrive on the Pro tier, alongside custom and shared templates.

Notta comes at this from transcription rather than from meetings, and the shape of the product follows. Speaker identification costs nothing, file uploads are a first-class feature rather than an afterthought, and the language list is both long and actually published — which is worth more than a large advertised number when the question is whether your language is on it.

The free plan needs reading carefully. It allows a hundred and twenty transcription minutes a month, which sounds workable, but caps each conversation at three minutes. That is shorter than any meeting it would be used for, so in practice the free tier demonstrates the product rather than running it. No payment details are required to start, which is a genuine courtesy.

The catch is that the free plan is a demonstration rather than a tool. Paid tiers lift the caps and add transcript translation on Pro and CRM and Zapier connections on Business. The vendor documents GDPR compliance. If your requirement is broad language coverage with accurate text and you are willing to pay from the outset, this is a strong fit; if you wanted to try it properly first, the three-minute ceiling will frustrate you.