German transcription: audio and video to text

By the Potok teamUpdated ~2 min read

German is among the strongest languages in Potok: published tests of the large-v3 model report word error rates between 4.3 and 5.8. Send voice messages, audio or video to the Telegram bot and get German text back, with files up to 2 GB accepted.

Transcribe a recording

Send your voice message, audio or video to @potok_now_bot on Telegram and the text comes back in the chat.

Open @potok_now_bot in Telegram

Files up to 2 GB · export to TXT, MD, DOCX, PDF, SRT and VTT · speaker labels and timestamps · about 30 languages

Key facts

  • Published large-v3 results for German run from 4.3 to 5.8 word error rate, measured by others and not by us.
  • Three sources agree that German sits near the low end of the table.
  • Long compound nouns are written as one word, and every noun starts with a capital letter.
  • The letters ä, ö, ü and ß should be checked after any copy and paste.

What a transcript looks like

Sample sentence in German
[00:00] Speaker 1: Lassen Sie uns die Besprechung beginnen. Zuerst gehen wir die Ergebnisse der letzten Woche durch, danach planen wir die nächsten Schritte.

Meaning in English: Let's start the meeting. First, we'll review last week's results, then plan the next steps.

Written by us to show the script and the layout of a transcript. It is not the output of the recognition engine.

Published quality

Quality for this language
LanguageVerdictPublished resultNotes
German (Deutsch)Recommendedword error rate 4.3% (large-v3, FLEURS)
Canary-1B-v2 paper, Whale paper, TheWhisper benchmark
Published tests show a low error rate for this language.
Published large-v3 results range from 4.30 to 5.8.

These numbers come from published tests by other people, not from tests by Potok. Your own audio, with its noise, accents and microphone, will differ.

How to do it

  1. Begin in Telegram. Open @potok_now_bot and send the German recording.
  2. Choose how to send. A chat attachment or a link is fine; a file nearing the 2 GB cap goes through the Upload button in the mini app.
  3. Mark the speakers. Turn on labels and timestamps for seminars and interviews.
  4. Check capitals and compounds. Scan nouns for capital letters and long compounds for splits.
  5. Check formal address. Make sure Sie, Ihnen and Ihr are capitalised where the document needs it.
  6. Export. Save as TXT, MD, DOCX, PDF, SRT or VTT.
What Potok can do
FeatureDetails
Where it worksTelegram bot @potok_now_bot; large files go through the bot's mini app
File sizeUp to 2 GB
ExportTXT, MD, DOCX, PDF, SRT, VTT
Speakers and timeSpeaker labels and timestamps can be switched on
LanguagesAbout 30 languages with good published results; a few more with warnings
TranslationThe transcript is not translated into another language
DictationA separate Potok desktop app lets you dictate text into any program; it recognises Russian speech

Common mistakes

Common mistakes and how to fix them
MistakeWhat happensFix
Not checking regional speechSwiss and Austrian German are not reported separately in the published figure.Send a sample from your speaker first.
Splitting compounds into several wordsThe result reads like English and breaks German spelling rules.Rejoin compounds during editing.
Replacing ß or umlauts with plain lettersWords change meaning, for example schon and schön.Keep the text in UTF-8 and search for the pairs.
Quoting the range as our own accuracyIt is a published figure.Say it comes from other people's tests.

More

See the full list of languages, the tools and the glossary.

Frequently asked questions

How accurate is German transcription?

Published tests of the large-v3 model give a word error rate of 4.3 to 5.8 for German. They are others' numbers.

Does it write nouns with capitals?

Usually yes, but review it. Capitalisation is a standard part of German spelling.

Does it understand Swiss German dialects?

The published figure does not cover dialects separately, so test a clip first.

Can I get subtitles for a German video?

Yes. Export SRT or VTT, then proofread the lines.

Will the bot translate into English?

No. The German speech is written down in German, and no translation step is offered.

Sources

Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.

  1. Word error rate (Wikipedia), Wikipedia · checked
  2. Whisper speech recognition system (Wikipedia), Wikipedia · checked
  3. Canary-1B-v2 paper, Table 11 (Whisper large-v3 on FLEURS) · checked
  4. Whale paper, Table 5 (Whisper large-v3 on FLEURS) · checked
  5. TheWhisper benchmark (turbo, average over FLEURS, MLS, Common Voice) · checked

Try it on your own recording

Send your voice message, audio or video to @potok_now_bot on Telegram and the text comes back in the chat.

Open @potok_now_bot in Telegram