To convert Italian audio to text, send the recording to the Potok bot on Telegram. Published tests of others on the large-v3 model, not our measurements, give a word error rate of 2.31 for Italian, one of the lowest in the list. 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
- A word error rate of 2.31 means roughly two wrong words in every hundred in those test recordings.
- Italian marks stress with accents on final vowels, so a missing accent can turn one word into another.
- Apostrophes join words when a vowel is dropped, as in an article joined to a noun, so check how they were split.
- Doubled consonants change meaning in Italian, which makes them a useful spot check.
- Southern and northern speakers differ in pronunciation, yet the written output follows standard Italian spelling for most words.
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
- Choose the clearest take. If you have both a phone clip and a studio file, pick the studio file. Fewer artefacts mean fewer wrong words to repair.
- Open the bot. Open @potok_now_bot in Telegram and attach the recording as audio, as a document, or forward a voice note.
- Handle a large file. A lecture or a long call can reach 2 GB. Press Upload in the bot's mini app for anything the chat attachment refuses.
- Scan the accents. Read a paragraph and look at the final vowels. An accent that is missing or wrong is quick to fix in the editor.
- Save in the format you need. TXT or MD for notes, DOCX or PDF to share, SRT or VTT if the text will become subtitles.
| 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 |
|---|---|---|
| Ignoring doubled letters | Words that differ only by one consonant read as a different word. | Search the text for the terms you care about and spell them out. |
| Sending a dialect-heavy clip and expecting standard spelling | Regional speech is written as heard, so forms can look odd. | Normalise the spelling by hand where your readers expect standard Italian. |
| Treating 2.31 as a promise | It is an average from other people's tests on clean speech. | Proofread names, figures and quotes. |
| Pasting into a form that strips accents | Final-vowel accents vanish and meaning shifts. | Keep the DOCX copy as your master. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Is Italian one of the strongest languages here?
On the published numbers, yes: 2.31 on large-v3 is among the lowest figures, though names and numbers still deserve a read.
Can I upload an Italian video instead of audio?
Yes. Video files and YouTube links go through the same path, inside the 2 GB limit.
Where does the 2.31 come from?
From published tests by other people on large-v3, not from our own measurements on your recordings.
Will the bot tell me who spoke?
It can add numbered labels such as Speaker 1 if you switch them on, but it never knows real names.
Does the text come back in another language?
No. The transcript stays in Italian, the language of the recording.
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