Upload the recording or paste a link. The interview comes back as German text — what was said, in the language it was said in — with each turn marked in the transcript view and every word timed. Files over 500 MB continue on the upload page. A pack from $4 opens the full transcript · packs from $4 for 500 minutes.
How it works
Expert interviews, fieldwork and long conversations.
Put the file in the box above or paste a link. Up to 500 MB goes straight in; longer recordings continue on the upload page, up to 10 hours or 5 GB.
Numbered speaker labels mark each turn in the transcript view, so question and answer are visibly separate even in a two-hour conversation.
Click a word to hear it again, then export TXT, DOCX, SRT, VTT, MD or JSON.
Which German
One thing is genuinely harder than the rest, and it is worth knowing before you record.
Recordings from Germany, Austria and Switzerland are handled as one language. Austrian Standard German and Swiss Standard German transcribe cleanly.
Schwiizerdütsch spoken broadly sits much further from the written standard than an accent does. Expect to read those interviews against the audio, and prefer Standard German if you have the choice when recording.
Long compound nouns are written as single capitalised words rather than split apart, which matters when you search the transcript for a term months later.
A formal interview stays formal on the page. The pronoun and the verb form that follows it are part of the record and are not normalised.
Working with the text
For research interviews, expert calls and reporting.
German puts the verb at the end of a subordinate clause, so the meaning often lands in the last three words. Cutting a quote early changes it more than it would in English.
TXT, DOCX, SRT and VTT contain the words without speaker labels. JSON is the export that keeps the speaker of every segment.
Packs from $4, credits never expire and readable in full, at any length, which covers a long Experteninterview without a pack.
ä, ö, ü and ß are written as spoken usage requires. Swiss texts use ss where German and Austrian ones use ß, and the transcript follows the speaker.
Pricing
A pack from $4 opens the full transcript. After that, one-time packs: $8 for 1,000 minutes, $12 for 2,000 minutes and $24 for 5,000 minutes. Credits never expire.
Ten expert interviews of an hour come to 600 minutes, inside the $8 pack of 1,000 — around $0.48 an interview.
FAQ
Yes. The transcript is the German that was spoken, written down. It is not converted into English — German audio produces German text.
Swiss Standard German transcribes cleanly. Broad Swiss German dialect is considerably harder, because it differs from the written standard in vocabulary as well as sound, so plan to review those recordings.
In the transcript view each turn carries a numbered speaker label, so an interview reads as an exchange. The labels are numbers rather than names.
No. TXT, DOCX, SRT and VTT hold the words only. JSON is the single export that records which speaker said each segment.
They are written as one capitalised word, the way German writes them, rather than being broken into pieces — which keeps them findable when you search the transcript.
Up to 10 hours or 5 GB per file. The box on this page takes up to 500 MB and larger files continue on the upload page.
DOCX or TXT for reading and coding, MD for a plain-text workflow, and JSON when you need the speaker and timing of each segment in your own tools.
Instant preview, no signup. A pack from $4 opens the full transcript.