Meetings

Record or upload meetings, transcribe them automatically with speaker separation, and turn them into minutes, action items and other documents.

The Meetings module turns spoken meetings into searchable, structured text. You record a meeting directly in your browser, upload an existing audio or video file, or (where set up) send a recording bot into your online meeting. Kasimir transcribes the recording with automatic speaker separation, then produces full minutes with a summary and action items, and lets you generate further documents such as follow-up emails or decision lists at the click of a button. Transcription runs GDPR-compliant on Kasimir's own servers in Germany – no US transcription service is used. The summary is produced by an AI model enabled for your company that runs in Germany or the EU.

What you can do with this module

• Record a meeting live in the browser (microphone).

• Upload an existing recording (audio or video).

• Invite a recording bot into an online meeting (Teams, Zoom, Google Meet) – if enabled for your workspace.

• Read the transcript with timestamps and speakers and jump along in the audio.

• Give the detected speakers (SPEAKER_00, SPEAKER_01 …) real names.

• Generate various documents from the transcript (minutes, task list, follow-up email and more) and export them as Markdown, Word or PDF.

• Ask questions about the meeting in the Ask-AI tab.

• Save summary and action items (and the transcript if you like) as a knowledge page in the notebook so chat can use it.

Capturing a meeting

On the Meetings page you find two cards at the top: Upload or record a meeting (upload a file or record live in the browser) and the card for inviting the bot. The same options exist in the Meetings tab of a project or team – the meeting then lands there right away.

Option A – Invite a bot to a meeting

1. Paste the invite link of your online meeting into the field (Teams, Zoom or Google Meet).

2. Click the invite button. The bot joins the meeting as a participant (Kasimir Notetaker) and records the audio.

3. Right away, an entry with the live status appears at the top of your meetings list: Requested …, Joining …, Waiting in the lobby (then admit it in the meeting), Audio recording in progress with a running clock, then Creating transcript … and Creating summary … until Done. A bar shows the stages Join · Recording · Processing · Done.

4. Use Stop to take the bot out of the meeting early. Once the recording has been handed over, the entry turns into the meeting in the same spot, which you open with a click. If something went wrong, it offers Invite again.

Supported platforms are Teams, Zoom and Google Meet. Other links are rejected with an error.

Option B – Upload a recording

1. Click the upload area (Upload meeting) and choose a file – or drag it onto the area.

2. The upload starts automatically; progress is shown as a percentage.

Supported formats and limits:

Option C – Record live in the browser

Below the upload area – after “or record” – sits the recorder.

1. Click Record and grant microphone access.

2. While recording you see a waveform visualization, a blinking record dot and the running duration. The screen stays awake (no sleep) while recording.

3. Use Stop & upload to end the recording; it is uploaded and processed automatically.

What happens after capture

Every recording automatically goes through several phases in the background. You don't have to wait – the list and detail page refresh on their own.

1. Pending – the recording is queued.

2. Transcribing… – speech is converted to text and speakers are detected.

3. Summarising… – minutes, summary and action items are generated.

4. Ready – the recording is fully analysed. (On problems: Failed with an error message.)

On the detail page an animated progress indicator shows the steps Upload → Transcribe → Summarise.

The meeting detail view

Clicking an entry in the list opens the meeting. At the top you see the title, date, language code and the number of detected speakers. Use the pencil icon to rename the title and the trash icon to delete the meeting (with a confirmation).

Below sits the audio player, which is linked to the transcript, plus four tabs.

"Summary" tab

Shows the automatically generated Markdown minutes (with sections such as participants, topics, decisions) and, beneath it, the suggested actions as a task list with owner and due date where identifiable.

“Transcript” tab

This holds the full transcript organised by speaker and timestamp.

• At the top you find the chapters: Generate chapters splits the meeting into sections with timestamps; a click jumps there in the audio.

• Each line shows the timestamp on the left and the colour-coded speaker. Clicking a line jumps the audio to that point; the line currently being spoken is highlighted and scrolled into view.

• Below that you can name the detected speakers: type the real name into the field next to SPEAKER_00 etc. Use Listen to play a short voice sample of that speaker to identify them. Then click Save.

"Templates" tab

Here you generate ready-made documents from the transcript. Generate output opens a list of templates.

Available templates (group Formats):

Under By meeting type there are seven more templates tailored to particular kinds of meetings: Sales call, Interview, 1:1 meeting, Daily / standup, Project status, Training / lecture and Workshop / brainstorm.

1. Choose a template. For Custom template a text field appears where you describe in your own words what should be generated (up to 2000 characters), then click Generate.

2. The new output appears as a card with the status generating … and fills in automatically once finished.

3. On a finished card you have: Copy (to clipboard), Export, Save as knowledge page and Delete.

Export formats: Markdown (.md), Word (.docx) and PDF (.pdf).

“Ask-AI” tab

Here you ask questions about the meeting – Kasimir answers based on its transcript and summary. Suggestions such as “Summarize the meeting” help you get started; Open in full chat → continues the conversation in the regular chat.

Save as knowledge page

At the bottom of the detail view you find Save as knowledge page. In the dialog you choose the title, where the page should live (Company-wide, Team, Project or Personal – wherever you may write) and what goes in: by default Summary & action items, optionally Append full transcript. Kasimir creates a notebook page from it; afterwards the view shows Saved to the notebook with the link Open page. If the target reaches beyond the meeting’s current audience, only the person who recorded it may do this.

Visibility and organisation

• Private by default: A meeting is only visible to you (its creator) – marked with the Private badge. Others in the company can't see it.

• Project-scoped: use Assign project to assign a meeting to a project; it then becomes visible to all members of that project.

• Team-scoped: use Assign team to assign a meeting to a team; all members of that team can then see it. Projects and teams also have their own Meetings tab for recording, uploading and inviting the bot.

• Filter: Above the list you filter using the All, General (no project) buttons and one button per project.

Tips & limits at a glance

• Maximum file size: audio 200 MB (MP3, MP4, M4A, WAV, WebM, OGG), video 1 GB (MP4, WebM, MOV – only the audio is processed).

• Bot: by default at most two at the same time per company, only Teams/Zoom/Google Meet; if the bot is not set up, the card is missing.

• Bot recording: at most 3 hours per invite; the bot then leaves the meeting automatically.

• Language: transcription is optimised for German.

• Excel export is visible in the menu but currently non-functional – use Markdown, Word or PDF.

• Recovery: interrupted browser recordings can be finalised afterwards.

• If you leave the page during processing, nothing is lost – the analysis keeps running in the background.