Who said what
Each passage carries a speaker and a timestamp — most of the typing in qualitative interviews is done.
Research · Thesis · Journalism
Transcribe interviews — with speaker separation
Typing up one hour of interview by hand takes four to six hours. Upload the recording here and get a transcript that separates interviewer and interviewee — with timestamps for quotes and citations.
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 an interviewHow it works
- Step 1
Upload the recording
Voice recorder, phone or Zoom recording: MP3, M4A, WAV or MP4 up to 100 MB — or paste a link.
- Step 2
Set the number of speakers
For two people, choose “2 speakers”. With a plan, Microsoft MAI-Transcribe-2 separates the voices.
- Step 3
Edit in Word
Export to Word, replace “Speaker 1/2” with I and R, and check quotes at the timestamp.
What you get
Up to 4 hours per file
Long semi-structured or expert interviews fit into one run with a plan.
Word, PDF, TXT
Word for editing, TXT for MAXQDA or ATLAS.ti, PDF for your appendix.
Encrypted history
With an account, your transcripts are stored encrypted and can be deleted one by one.
At a glance
- Speaker separation comes with the day pass (€2.99), credit (€4.99) or Pro — the free trial gives plain text.
- Recognition often drops fillers like “um”. For strict verbatim transcription by fixed rules, you need to correct afterwards.
- Get your interviewees' consent before recording — including processing by a transcription service.
- 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
Is the transcript good enough for my thesis?+
As a basis, yes; as the final version, no. Check names, terms and quotes at the timestamp and adapt the transcript to your department's transcription rules.
Does it know who is the interviewer?+
It separates voices as “Speaker 1” and “Speaker 2”. You assign the roles — find and replace in Word is enough.
May I transcribe interviews with an online service?+
Usually yes, if your interviewees consented. The file is processed without storage at the AI provider (zero data retention); see the privacy policy. For sensitive data, ask your supervisor or ethics board.
What does a one-hour interview cost?+
With the day pass, €2.99 for 24 hours, no matter how many interviews you upload in that time. For several sessions, credit or Pro pays off.
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.