Bosnian transcription that holds up.
Bosnian is where most transcription tools quietly fall apart. Canto is built to handle it, and we publish the numbers rather than describing them.
≤5%
Canto AI
16.6%
Industry-standard engine
3.3× fewer errors · word error rate on FLEURS, lower is better
How Canto handles this language
Bosnian, Croatian and Serbian share most of their grammar and vocabulary, which sounds like it should make them easy and in practice does the opposite: engines trained mainly on one of them tend to flatten the others toward it, or transcribe into the wrong alphabet entirely. Canto treats Bosnian as its own target, keeps the Latin script, and holds up on the ijekavian forms and Turkish-origin loanwords that general-purpose engines tend to smooth away.
No public per-language figure yet for this language; the current model sits in the top accuracy tier (under 5% error), which is what we cite here.
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
How accurate is Bosnian transcription?
Canto's current model sits in the top accuracy tier for Bosnian, under 5% word error rate. The engine most other notetakers build on scores 16.6% on the same public benchmark.
Does it handle mixed Bosnian and English?
Yes. Language detection is automatic and works mid-sentence, so a meeting that switches between Bosnian and English is transcribed correctly without you changing a setting.
Can I get summaries and notes in Bosnian?
Yes. The app interface and everything the AI writes (titles, summaries, action items, chat answers) ships in Bosnian. Transcription itself covers 99 languages regardless of which one you pick for the interface.
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.