German Audio to Text
Drop in German audio or paste a link and get back a clean, timestamped transcript – compound words, umlauts and ß intact, dialects and all.
Accepts German audio or video – MP3, M4A, WAV, MP4 and more, or a link · returns a clean, timestamped German transcript with correct umlauts and ß.
60 min free · no card required · we never train on your audio
How do I convert German audio to text?
Upload your German file or paste a link, and Pepys writes the speech out as a clean, timestamped transcript in minutes. It is tuned for Hochdeutsch but also for Austrian German and Swiss German (Schweizerdeutsch), which sound less like an accent and more like a separate language. Spelling stays correct – the ß, the ä/ö/ü, and the long compound nouns come back whole. German is auto-detected among 99+ languages, and the first 60 minutes are free, no card.
How german audio to text works
Upload or paste a link
Drop in a German recording or paste a link – any format, nothing to install.
Get your transcript
Pepys writes the German speech out as timestamped text in minutes, ß and umlauts intact.
Edit and export
Fix a name or term inline, then export to TXT, Markdown, DOCX, PDF, SRT, VTT, or JSON.
German is the first language of roughly 100 million people across Germany, Austria, Switzerland, Liechtenstein and beyond, and "German" covers a lot of ground. A Hamburg podcast, a Viennese interview and a recording in Bern are three different listening experiences – Swiss German in particular drifts so far from Hochdeutsch that German speakers themselves often need subtitles. Pepys is built for that spread, so a lecture, an interview, a voice memo or a Sprachnachricht comes back as text you can search, quote and translate.
Two things tend to defeat off-the-shelf speech models in German, and Pepys is built around both. One is the language's love of stacking nouns into a single word – Geschwindigkeitsbegrenzung, Krankenversicherungsbeitrag – where one wrong boundary scrambles the whole term. The other is the verb-at-the-end clause, where the word that carries the meaning only lands at the very end of a long sentence. We keep those intact, render the ß and ä/ö/ü correctly, and auto-detect German among 99+ languages. Your first 60 minutes are free, credits never expire, and we never train on your audio.
Clean paragraphs. No more um's and ah's.
The left is what Pepys hands back – logical paragraphs with the filler stripped out, punctuated and readable. The right is the raw, one-line-per-segment dump most transcribers leave you with.
um so yeah everyone keeps telling you to like lead with your best line right but uh honestly if you give away the whole answer in the first second you know there's basically no reason for anyone to keep watching so the hook isn't kind of the smartest thing you say it's like a loop you open that they need to close and um that's the part that actually keeps people around
RawAccurate across Hochdeutsch, Austrian German, and Swiss German (Schweizerdeutsch) – not just one studio accent
Long compound nouns and verb-final sentences kept whole; ß and ä/ö/ü rendered correctly
Timestamps and per-chunk speaker labels · export to TXT, Markdown, DOCX, PDF, SRT, VTT, or JSON
99+ languages including German, auto-detected · we never train on your audio · credits never expire
Any language – 99+ detected automatically
- English
- 中文
- Español
- العربية
- हिन्दी
- Français
- 日本語
- Português
- Русский
- Deutsch
- 한국어
- Italiano
- বাংলা
- Türkçe
- فارسی
- Tiếng Việt
- தமிழ்
- Polski
- ไทย
- Українська
- Nederlands
- עברית
- Ελληνικά
- తెలుగు
- Bahasa Indonesia
- اردو
- Svenska
- मराठी
- Română
- Magyar
- Čeština
- ગુજરાતી
- Kiswahili
- ქართული
- Tagalog
- አማርኛ
Works with the platforms you live in.
Paste a link from YouTube, TikTok, Instagram, Facebook, Spotify, or Apple Podcasts – or drop in any audio or video file. We transcribe it once, then you export it however your workflow needs.
- YouTube
- TikTok
- Spotify
- Apple Podcasts
- or any file
Export to any format
- TXT
- Markdown
- DOCX
- SRT
- VTT
- JSON
Timestamps, speaker labels, and subtitle timing carry through to every export.
German audio to text – questions, answered
How do I convert German audio to text?
Upload your German file or paste a link on this page – the first 60 minutes are free, no card. Pepys writes it out as clean, timestamped German text in minutes, ready to edit and export.
Can it cope with Swiss and Austrian German?
Yes. Hochdeutsch is the easy case; Pepys is also built for Austrian German and the Swiss German (Schweizerdeutsch) that diverges far enough to feel like its own language. Anything it mishears you can fix inline before exporting.
What actually makes German hard to transcribe?
Two things. Compound nouns fuse several words into one, so a single wrong split breaks the term, and the verb often lands at the end of a long clause. Pepys is tuned for both, then lets you correct any word inline.
Do the umlauts and ß come out right?
Yes – ä, ö, ü and the sharp s (ß) are rendered correctly throughout, and you can adjust spelling or capitalisation inline before you export.
Is my German audio private?
Yes. We never train AI on your audio or transcripts, and you can auto-delete your files after processing.
More free tools
Keep reading
Don't just take our word for it.
Ask ChatGPT, Claude, or Perplexity what Pepys is and who it's for. One click, and your favorite AI does the homework.
German audio to text – free to start
Pay as you go – credits never expire, nothing to cancel. Or start free with 60 minutes, no card.