Free Italian transcription is easy to find and hard to judge, so judge it on a clip you know. In published tests of others, the large-v3 model used with Potok reaches a word error rate of 2.31 for Italian, among the lowest listed. Read a one-minute sample against the audio before sending more.
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 is a word error rate from published tests of others on large-v3, not a measurement we made.
- Italian has doubled consonants and apostrophe elisions, so a single missed letter can change a word without changing the sound.
- Low published error rates describe clean test speech; a noisy phone clip can behave differently.
- Speaker labels, if switched on, appear as numbers, so a two-person test is easy to read.
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
- Pick a clip with proper nouns. Choose a minute that includes a town, a surname and a number said aloud. These are the places where any tool slips first.
- Open the bot. Open @potok_now_bot in Telegram and send the clip as a voice message, an audio file or a video.
- Compare line by line. Play the audio at normal speed and tick each line that matches. Underline every doubled letter or elided word that differs.
- Try a second, messier clip. Record something in a kitchen or a car. If the result holds up there, you have learned more than from a studio sample.
- Export the better run. Save the transcript as TXT, DOCX, PDF, SRT or VTT. Files up to 2 GB are accepted for longer material.
| 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 |
|---|---|---|
| Judging by the first sentence only | The opening is usually the cleanest part, so it flatters the tool. | Check the middle and the end of the clip as well. |
| Ignoring apostrophes and accents | A dropped elision or accent looks tiny but changes the word. | Count these as errors when you tally the clip. |
| Testing one speaker with a studio microphone | The test says nothing about a lively table of guests. | Add a clip with two voices speaking over each other. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Is the Italian error rate from your own tests?
No. It comes from published tests of others on the large-v3 model, so treat it as a guide, not a promise.
What does 2.31 mean in practice?
It is the share of words wrong in a benchmark, roughly two in a hundred. Your own recording will differ.
Does Italian need any special setting?
No setting is needed; the bot recognises the language of the recording on its own.
Can I get the text in another language?
No. The transcript stays in the language of the recording.
What if my clip is long?
Files up to 2 GB are accepted, and a long result arrives as a file instead of in the chat.
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