Speakers and timestamps
See who said what and jump straight to that moment in the recording. Check speaker labels if voices overlap or the audio isn't clear.
Meeting minutes
Meeting minutes
Draft meeting minutes from the transcript, with decisions and follow-up items pulled out for you to review.
Live demo
Runs in your browser.
Put the recording to work
Keep proposals separate from approved decisions and check the recording to confirm who is responsible for what. Have the right participants approve the minutes before you treat them as an official record.
A transcript you can review and use
Search and edit
Find a name or topic without listening to the whole file. Check the audio to fix names and technical terms.
Summaries and translation
Generate a summary, ask questions about the transcript, or translate it. Always check AI answers against the source before sharing.
Documents and subtitles
Export to text, Word, PDF, or SRT subtitles. Check the wording and timing before you send it out.
From recording to a usable record
Record or upload
Upload an audio or video file you already have, or record directly in the app. Only use recordings you have permission to use.
Transcribe
Get editable text with speaker labels and timestamps.
Review and organize
Re-listen to any unclear parts, fix terms, and check the summaries, decisions, and tasks.
Export and share
Pick a format and send it to the people who need it.
For developers and AI agents
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.
Word timings and speakers
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.
SRT and translation
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.
Built for agents
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.Questions
Can I use an existing recording?
Yes. You can upload audio or video files you already have, or record in the app. No meeting bot needs to join your call.
What affects the result?
Background noise, overlapping voices, microphone placement, accents, and technical terms all play a role. Test a typical recording of yours and check the parts that matter.
Can I work across languages?
KolWrite transcribes in more than 100 languages and translates between them. Changing the site language only changes this page, not the language of your recording.
How do I turn a meeting recording into minutes and action items?
Start by transcribing the recording and generating a summary that pulls out decisions and action items. Since good minutes need to show who agreed to what, keep the speaker labels on and verify every item against the recording before sending the final version out.
Can I generate meeting minutes with my own language model?
Yes. Pull the timed, speaker-labeled transcript from KolWrite, either in the app or via the API, and feed it to your model. Always verify the output against the recording, since a model can make up an action item or assign it to the wrong person.
Try a recording from your own work.
Check the transcript, the summary, and the exported file to see if it fits your workflow.