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 separates a vague summary from minutes people can actually use, and the rules to know before you hit record (participant consent is not optional). Each method is laid out step by step, with its real limits: maximum length, quality in a six-person meeting, and how it handles accents and industry jargon.
Method 1: do everything in Skilzy's AI Lab
The most complete approach is to chain transcription and minute-writing together in a single environment, with credits already included, instead of juggling three subscriptions. That is the idea behind the AI Lab built into Skilzy: you get access to real AI tools straight from the platform, you learn the method while you use it, and you don't have to pay for a separate subscription at 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 your meeting tool's recording.
- Grab the audio file. Universal formats: MP3, M4A, WAV.
- Transcribe the audio into text. You'll get a raw block of text, 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 pulls out decisions and action items.
- Read it over and fix it. Budget 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 whole thing takes around 10 to 15 minutes, versus 45 to 90 minutes of writing it up by hand.
One thing worth knowing 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 phrase the request is 80% of the result. If you'd like a broader overview before choosing, start with our guide to learning AI as a complete beginner.
Method 2: the transcription already on your phone (free)
Your phone can probably transcribe a voice recording into text for free, with no extra app at all. 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, it's immediate, and in most cases the audio stays on the device.
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.
- Past 30 or 40 minutes, the text becomes hard to use as is.
- It doesn't produce any minutes. You still need an AI assistant for the synthesis step.
Method 3: your video call 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 lands in the organizer's Drive.
- Zoom: audio transcription is enabled in the account settings, on the cloud recording side, on paid plans.
One thing to watch: these features depend on your work subscription and on what your IT admin has allowed. On a free account, they're often unavailable. Check before the meeting, not during it.
Once you have the transcript, the job isn't done. A one-hour Teams transcript easily runs 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 call. They tell speakers apart and often offer an automatic summary. Almost all have a free tier capped at a certain number of minutes per month, then a monthly subscription. One caveat: your audio goes to their servers. Read up on where the data is hosted before sending 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, with 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. Handy, but a bot that shows up in a meeting without anyone announcing it raises a genuine consent problem. Avoid it without explicit agreement from the team.
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 your work 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 no one will read. Here's a template to copy and paste in front of your transcript:
You are writing the minutes of a meeting from 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, 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 the deadline isn't stated in the transcript, write “to be confirmed.” Don't make anything up.
- Open questions: topics raised without a conclusion.
- Useful quotes: a maximum of 3 short verbatim quotes worth keeping as they are.
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 the list of participants and the industry jargon before the transcript. The AI will write “GDPR” instead of “gee dee pee are,” along with the proper nouns from your field.
- Explicitly forbid invention. The instruction “don't make anything up, write to be confirmed” sharply reduces action items assigned to the wrong person.
- Split it up if the meeting runs over 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 on their free plans breaks down which one handles long text best. And if you want to practice without spending anything, we've rounded up 15 free resources in French.
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 on the right side of the rules.
Announce the recording and what it's for. One sentence at the start: “I'm recording so I can write up the minutes, and the audio will be deleted once they're approved. Is everyone okay with that?” If someone says no, you take notes instead. Participants must be informed before you start, and be able to object.
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 keep only what's necessary, for only as long as necessary.
Be careful with sensitive meetings. One-on-ones, health data, salary information, confidential client files: in those cases, either stick to a local solution (phone in offline mode, Whisper on your own machine), or don't record at all. 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 the help of AI, and have someone who was there read them over. 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 situation, test it on a short, low-stakes meeting, then adjust the prompt until you get a document your colleagues actually read.
