You just walked out of a one-hour meeting. Roughly 9,000 words were spoken (based on 150 words per minute), and you remember three of them. Transcribing a meeting with AI means turning that audio into text in a few minutes, then asking an assistant to produce structured minutes: decisions made, action items, owners, deadlines. No technical skills required, and two of the methods below cost nothing.
This guide gives you four methods, from the most complete to the simplest, the exact prompt that makes the difference between a vague summary and minutes people can actually use, and the rules to know before you hit record (participant consent is not optional). Each method is described step by step, with its real limits: maximum length, quality in a six-person meeting, handling accents and industry jargon.
Method 1: do everything in Skilzy's AI Lab
The most complete approach is to chain transcription and minute-writing in a single environment, with the credits already included, instead of juggling three subscriptions. That's the idea behind the AI Lab built into Skilzy: you access real AI tools from the platform, you learn the method while you use it, and you don't have to pay a separate subscription for every step.
Here's how it works, in five steps:
- Record the meeting. A phone in the middle of the table is enough for six people in a normal room. For video calls, start the meeting tool's own recording.
- Grab the audio file. Universal formats: MP3, M4A, WAV.
- Transcribe the audio into text. You'll get a raw block, with imperfect punctuation and the occasional misheard word. That's normal, and it won't cause problems later.
- Apply the minutes prompt (the one in section 5 of this article). The assistant cleans up, structures, and extracts the decisions and action items.
- Proofread and fix. Allow two to three minutes. Check the numbers, the proper nouns, and the deadlines: those are the three places where AI gets it wrong most often.
For a one-hour meeting, the total comes to around 10 to 15 minutes, versus 45 to 90 minutes of writing it by hand.
One thing to know before you sign up: two state-recognized certifications are eligible for funding (RS7439 for AI-assisted content marketing, RS6792 for AI and sales) if you want to go further than meeting minutes.
The real value for a beginner isn't the tool: it's the method. Knowing how to frame the request is 80% of the result. If you want a broader overview before choosing, start with our guide to learning AI as a beginner.
Method 2: the transcription already on your phone (free)
Your phone can probably transcribe a voice recording into text, for free and without any extra app. It's the fastest option for a short meeting, and it would be dishonest not to mention it.
On iPhone (iOS 18 and later): open the Voice Memos app, record, then tap the transcription icon at the top of the recording. The text appears, and you can copy and paste it into an AI assistant.
On Android: the Recorder app on Pixel phones transcribes live, including offline. On Samsung, the Voice Recorder app offers a “Speech to text” mode. On other brands, open the Google Docs app, then Tools, then Voice typing.
What this method does well: it's free, immediate, and the audio stays on the device in most cases.
Its limits, plainly stated:
- It doesn't tell speakers apart. You get a block of text with no idea who said what.
- Quality drops fast if several people talk at once or the room echoes.
- Beyond 30 or 40 minutes, the text becomes hard to use as is.
- It produces no minutes at all. You still need an AI assistant for the synthesis step.
Method 3: your video conferencing tool's built-in transcription
If your meeting is on Teams, Google Meet, or Zoom, transcription is already built in and it identifies speakers by name. That's an advantage the other methods don't have, because the tool already knows who's connected.
- Microsoft Teams: during the meeting, go to the “More actions” menu, then “Start transcription.” The text is timestamped and attributed to each participant, then archived with the meeting.
- Google Meet: transcripts are available depending on your organization's Google Workspace edition, and the document is saved to the organizer's Drive.
- Zoom: audio transcription is enabled in the account settings, on the cloud recording side, on paid plans.
The thing to watch: these features depend on your business subscription and on what your IT administrator has allowed. On a free account, they're often unavailable. Check before the meeting, not during it.
Once you have the transcript, the work isn't over. A one-hour Teams transcript easily runs to 40,000 characters, unreadable as is. You still go through an AI assistant for the synthesis.
Method 4: specialized third-party tools
Dedicated transcription tools are the most accurate on long, multilingual meetings, but they add yet another subscription or require a technical setup.
Three families, depending on your profile:
Consumer online tools (Notta, Tactiq, Fireflies, Happy Scribe). You upload a file or connect them to your video calls. They tell speakers apart and often offer an automatic summary. Almost all of them have a free tier limited by minutes per month, then a monthly subscription. One caveat: your audio goes to their servers. Read up on where the data is hosted before you send a confidential meeting their way.
Whisper, the open source model. Released under the MIT license, Whisper is publicly documented on GitHub and installs on your own computer. Free, no length limit, and the audio never leaves your machine. In exchange, you have to use the terminal and accept a processing time that depends on your hardware. It's the best option if confidentiality is non-negotiable and a command line doesn't scare you.
Assistants that connect to your calendar and join meetings on their own. Convenient, but a bot that invites itself into a meeting with no one announcing it raises a real consent problem. Avoid it without the team's explicit agreement.
Quick comparison of the four methods
| Method | Entry cost | Identifies speakers | Structured minutes | Level required |
|---|---|---|---|---|
| Skilzy AI Lab | Monthly subscription | Via the prompt and your notes | Yes, with the method provided | Beginner |
| Phone (built-in) | Free | No | No | Beginner |
| Video call tool | Included depending on business plan | Yes | Partial | Beginner |
| Third-party tool / Whisper | Limited free tier or self-install | Yes | Often | Intermediate |
The prompt that turns 9,000 words into readable minutes
Good minutes don't come from the transcription tool but from the prompt you write afterwards: ask for a precise structure and named action items, never “summarize this meeting.” “Summarize” produces a lukewarm paragraph nobody will read. Here's a template to copy and paste above your transcript:
You are writing the minutes of a meeting based on the raw transcript below. The transcript contains speech recognition errors: correct them when the meaning is obvious, and flag uncertain passages in square brackets.
Produce exactly these five blocks:
- Context in 3 lines maximum (purpose of the meeting, identifiable participants).
- Decisions made: one bullet per decision, phrased in the past tense and affirmatively.
- Action items: a table with Action, Owner, Deadline. If the owner or deadline isn't stated in the transcript, write “to be confirmed.” Invent nothing.
- Open questions: topics raised without a conclusion.
- Useful quotes: 3 short verbatim quotes maximum that are worth keeping as is.
Constraints: 400 words maximum in total, factual tone, no evaluative adjectives. Ignore off-topic digressions.
Transcript: [paste here]
Three tweaks that change the result:
- Give it the participant list and the industry jargon before the transcript. The AI will write “GDPR” instead of “gee dee pee are,” and get the proper nouns in your field right.
- Explicitly forbid making things up. The instruction “invent nothing, write to be confirmed” sharply reduces action items assigned to the wrong person.
- Split it up if the meeting runs past 90 minutes. Process the transcript in two or three chunks, then ask for the partial minutes to be merged.
Which assistant you pick matters less than the prompt, but it does matter a little. Our comparison of ChatGPT, Claude, and Gemini in their free versions breaks down which one handles long text best. And if you want to practice without spending anything, we've rounded up 15 free resources.
Before you hit record: consent and data
Recording a work meeting without telling the participants is illegal in France, whatever transcription method you use. Three habits are enough to stay within the rules.
Announce the recording and what it's for. One sentence at the start: “I'm recording this so I can write the minutes; the audio will be deleted once they're approved. Does that work for everyone?” If someone objects, you take notes instead. Participants have to be informed before you start, and be able to opt out.
Limit how long you keep it. Keep the minutes, delete the audio and the raw transcript once the document is approved. Data minimization is at the heart of the GDPR as the CNIL explains it: you only keep what's necessary, for as long as necessary.
Be careful with sensitive meetings. One-on-ones, health data, salary information, confidential client files: in those cases, either you stick to a local solution (phone in offline mode, Whisper on your own machine) or you don't record. A free online service is not the right place for a performance review.
One last point people often forget: also tell people the minutes were written with AI help, and have someone who was there review them. Minutes approved by a human commit their author, not the tool.
Key takeaways
Four methods, one principle: transcription is the easy part, the minutes come from the prompt. Start with whichever method is most accessible in your context, test it on a short, low-stakes meeting, then adjust the prompt until you get a document your colleagues actually read.
