Speaker separation
With a plan, MAI-Transcribe-2 separates the voices, so you can see who raised which point.
Teams · Zoom · Meet · in person
Turn meeting recordings into text for your minutes
No bot joining your call, no app for every participant: upload the recording afterwards and get a transcript with speakers and timestamps. Write the minutes in minutes, not hours.
Free trial: 3 transcriptions per calendar month, each up to 10 minutes, no account — as plain text. Speaker separation (“who said what”) and files up to 4 hours are part of the paid offerings: day pass €2.99, credit €4.99, Pro €8.99/month.
Upload a meeting recordingHow it works
- Step 1
Get the recording
Teams and Zoom save recordings as MP4; Zoom also saves an M4A. In person, a phone in the middle of the table is enough.
- Step 2
Upload
For large video files, use the audio track (M4A) — it is usually ten times smaller.
- Step 3
Write the minutes
Open the transcript in Word, name the speakers, pull out decisions and action items.
What you get
No meeting bot
Nothing joins the call and no one installs anything. You decide after the meeting what gets transcribed.
Up to 4 hours
Retreats and long workshops fit into one run.
Word and PDF
Word to keep writing, PDF to file away — with speakers and timestamps.
At a glance
- Sprechverlauf produces a transcript, not finished minutes or a summary — you write the decisions yourself.
- Tell all participants before recording and get their consent.
- A conference mic or a phone in the middle of the table improves recognition in person a lot.
- Free trial without an account or login; plans from €2.99 one-off, no subscription required.
- Technical anti-abuse protection: currently up to five transcription starts per hour and files up to 100 MiB.
- Processed via OpenRouter with zero data retention: the AI providers store neither audio nor text; Sprechverlauf deletes audio files after processing and keeps transcripts only for signed-in users — encrypted.
- Premium: upload videos (MP4, MOV, WebM, up to 100 MiB), name speakers and review subtitles before exporting SRT or VTT.
- The video is deleted from our server one hour after upload. Your encrypted transcript stays in your account until you delete it. Only the extracted audio is sent for transcription.
Frequently asked questions
Where do I find the recording in Teams or Zoom?+
Teams stores recordings in OneDrive or SharePoint; download the MP4 from there. Zoom saves local recordings in the “Zoom” folder in your Documents, including an audio-only M4A.
Why not use Teams' own transcription?+
It often depends on licenses and admin settings and only works for Teams. Here any recording works — in person or from any other tool.
How many participants can it handle?+
Speaker separation copes with several voices; it works best when people take turns. With many similar voices, speakers may be merged.
Is confidential content stored?+
The AI provider stores neither audio nor text (zero data retention). Sprechverlauf deletes the file after processing; with an account, the transcript is kept encrypted until you delete it.
Do I need an account or a subscription?+
Not for the free trial. You only need an account to buy a plan (day pass, credit or Pro) — a subscription is never required. Technical anti-abuse limits apply.
How long is processing data retained?+
Recognition runs through OpenRouter with zero data retention — the providers (Microsoft Azure, DeepInfra, Groq) store neither audio nor text. Sprechverlauf deletes uploaded audio files after processing, at the latest after two hours, and keeps the transcript in memory for at most two hours. Only signed-in users get an encrypted copy in their account, which they can delete at any time.
Video uploads, speaker names and subtitles+
Premium: upload videos (MP4, MOV, WebM, up to 100 MiB), name speakers and review subtitles before exporting SRT or VTT. The video is deleted from our server one hour after upload. Your encrypted transcript stays in your account until you delete it. Only the extracted audio is sent for transcription.