Italian is one of the best-scoring languages for Potok. Published tests of the large-v3 model report a word error rate of 2.31, among the lowest figures on our list. Send Italian voice messages, audio or video to the Telegram bot; files up to 2 GB are 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
- The 2.31 word error rate is a published large-v3 result, not a measurement we made.
- It is one of the lowest published error rates among the languages listed here.
- A low average still hides mistakes in names, numbers and overlapping voices.
- Italian uses accents on final vowels and apostrophes in contractions like un'amica.
- Regional Italian accents and dialects are not reported separately in the published figure.
What a transcript looks like
[00:00] Speaker 1: Iniziamo la riunione. Prima esamineremo i risultati della settimana scorsa, poi pianificheremo i prossimi passi.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
| Language | Verdict | Published result | Notes |
|---|---|---|---|
| Italian (Italiano) | Recommended | word error rate 2.31% (large-v3, FLEURS) Canary-1B-v2 paper, TheWhisper benchmark | Published tests show a low error rate for this language. One of the lowest published error rates among the languages listed here. |
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
- Message the bot. In @potok_now_bot send the voice note, file, video or YouTube link.
- Go big if needed. A 2 GB file is the ceiling; the Upload button in the mini app handles heavy files.
- Add labels where useful. Speaker labels and timestamps are optional.
- Look at the final accent. Compare è with e and città-type words, because a missing accent changes the word.
- Check double consonants. Italian spelling doubles letters, so check pairs like casa and cassa.
- Export. TXT, MD, DOCX, PDF, SRT or VTT.
| Feature | Details |
|---|---|
| Where it works | Telegram bot @potok_now_bot; large files go through the bot's mini app |
| File size | Up to 2 GB |
| Export | TXT, MD, DOCX, PDF, SRT, VTT |
| Speakers and time | Speaker labels and timestamps can be switched on |
| Languages | About 30 languages with good published results; a few more with warnings |
| Translation | The transcript is not translated into another language |
| Dictation | A separate Potok desktop app lets you dictate text into any program; it recognises Russian speech |
Common mistakes
| Mistake | What happens | Fix |
|---|---|---|
| Skipping the review because the score is low | Names and figures can still be wrong. | Check the passages that matter. |
| Missing the accent on è | A verb turns into a conjunction. | Search the text for the short words. |
| Assuming regional dialects are covered | The figure reports Italian in general. | Test a clip from a strong dialect speaker. |
| Looking for speaker names | Labels are only numbers. | Rename them in the file. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
How accurate is Italian transcription?
Published large-v3 tests give a word error rate of 2.31 for Italian, among the lowest on our list. It is a figure from others.
Does that mean no mistakes?
No. Names, numbers, noise and overlapping voices still cause errors.
Is Italian better than French here?
In published large-v3 tests Italian shows 2.31 and French shows 5.3 to 6.31, though test sets differ, so compare with caution.
Are apostrophes handled?
Usually, but verify contractions such as l'anno and un'amica.
Can I transcribe an Italian interview?
Yes. Turn on speaker labels and timestamps for several voices.
Is the text translated?
No. The transcript stays in Italian, and translation into another language is not part of the bot.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- Word error rate (Wikipedia), Wikipedia · checked
- FLEURS speech dataset (Google, Hugging Face), Hugging Face · checked
- Canary-1B-v2 paper, Table 11 (Whisper large-v3 on FLEURS) · checked
- 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