Zoom
For cloud recordings, look under Recordings in the Zoom web portal. Local recordings are saved as files on the computer that recorded. Download the video or the audio file.
Theme
Zoom, Teams, and Google Meet
Download the recording from your meeting platform and upload it to KolWrite.
Live demo
Runs in your browser.
You will get a searchable transcript with speaker labels and timestamps, plus a summary ready to send out. No bot ever joins your call.
Every platform stores recordings in a different spot. What you can actually record comes down to your plan and the settings your administrator chose.
For cloud recordings, look under Recordings in the Zoom web portal. Local recordings are saved as files on the computer that recorded. Download the video or the audio file.
Depending on the meeting type, recordings go to OneDrive or SharePoint. Find the file in the chat or your files and download it.
If your plan includes recording, the file goes to the organizer's Google Drive. Open it in Drive and download it.
You can still record the meeting on your own.
KolWrite can capture your computer's own audio and your microphone at the same time, so you get both sides of the call.
If you are meeting in person, record the audio on your phone, Mac, or watch, then upload the file when you are done.
Recording a conversation requires consent in many places. Let the participants know first, and check the rules where you are.
Grab the audio or video file from Zoom, Teams, or Meet.
Drop the file into KolWrite. You can choose the spoken language yourself or let KolWrite detect it.
Listen back to any parts you aren't sure about and check the names and speaker labels. Once you assign a name to a speaker, KolWrite remembers them.
Generate a summary with decisions and action items, double-check it against the audio, and export to Word, PDF, or plain text to share.
You can also run everything KolWrite does with a recording through our API. Send the address of an audio or video file from your own code or an AI coding agent, and you'll get back the transcript with word timings, speaker labels, and an SRT file if you request one.
The JSON output gives you the start and end time for every segment, plus individual word timings on models that support alignment. Turn on speaker separation to include a speaker label on each segment.
Pass output_format as srt if you want subtitles directly from the API. If you are using the Oracle models, you can also set translate_to to get the text back in another language.
The API console publishes plain-text instructions for an agent to read before writing code. This includes agent-instructions.md, along with llms.txt, which links to the full reference.
Example request. The key comes from an environment variable, and the console has the full reference.
curl -X POST https://app.kolwrite.com/transcribe \
-H "x-api-key: $KOLWRITE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"audio_url": "https://example.com/meeting.m4a", "model": "oracle", "include_diarization": true, "output_format": "json"}'
# Returns {"jobId": "..."}. Poll GET https://app.kolwrite.com/transcribe/{jobId}
# until status is COMPLETED. The result is the file or the JSON you asked for.
Yes. Just download the video or audio file from Zoom and upload it to KolWrite. You will get a transcript with timestamps and speaker labels.
Find the recording in the Teams chat, OneDrive, or SharePoint, download it, and upload it to KolWrite. It will return a timestamped transcript with speaker labels, which you can then use to generate a summary and action items.
Yes. If your plan includes recording, Meet puts the file in Google Drive. Download it from Drive and upload it to KolWrite.
No. Since KolWrite processes the recording after the meeting ends, nothing joins the call and your platform doesn't need to allow third-party bots.
Yes. Speaker separation labels who is talking, keeps the timestamps, and lets you assign a name to each speaker. Check the passages where voices overlap or a microphone is weak, since those make it harder to tell who said what.
Yes. Send a recording's address to the KolWrite API to get back timestamped segments, plus speaker labels if you enable include_diarization. It also supports stereo recordings where each person is on a separate channel. Check the API console for full details and AI agent instructions.
Upload a recording, fill in the speaker names, and see how well the summary captures what you decided.