canto
AboutPricingContact
AccuracyDeutsch

German transcription for real meetings.

German is well served by most engines on clean audio and much less so on a real meeting with four people, compound nouns and a speakerphone. We publish where we land.

2.7%

Canto AI

4.5%

Industry-standard engine

1.7× fewer errors · word error rate on FLEURS, lower is better

How Canto handles this language

German punishes weak transcription in specific ways: compound nouns mean a single misheard fragment corrupts a whole word rather than one syllable, separable verbs put meaning at the end of a sentence, and the difference between Sie and sie changes who is being addressed. Canto is measured on the same public benchmark as every other language here, so the figure below is comparable rather than a marketing number.

What the benchmark measures

Word error rate counts every insertion, deletion and substitution against a human reference transcript, then divides by the number of words spoken. Lower is better, and 5% means roughly one wrong word in twenty. We measure on FLEURS, a public benchmark of read speech across many languages, so anyone can repeat the test rather than take our word for it.

How we measure

The same audio goes through both engines with no per-language tuning, and the output is scored with the same normalisation on both sides. We publish the competing engine's figure alongside ours rather than only our own, because a number with nothing to compare it to says very little.

What you get

  • Automatic language detection, including conversations that switch language mid-sentence
  • Speakers separated automatically, so the transcript reads like a script
  • AI titles, summaries and action items written in the language you choose
  • Search and chat across everything you record, with answers that cite the moment
  • A notetaker that joins Teams, Meet and Zoom, plus phone and watch recording in person
Questions

Questions

How accurate is German transcription?

Canto measures 2.7% word error rate on the public FLEURS benchmark, against 4.5% for the engine most other notetakers build on.

Does it handle Austrian and Swiss speakers?

Standard German as spoken in Austria and Switzerland transcribes normally. Strongly dialectal speech is harder for every engine on the market, ours included, and we would rather say so than claim otherwise.

Can I get summaries and notes in German?

Yes. The interface and everything the AI writes (titles, summaries, action items, chat answers) is available in German.

Try it on your own audio.

300 minutes a month, free forever. The fastest way to check an accuracy claim is to run your own recording through it.