Free Romanian transcription is easy to judge on a short, well-chosen clip. Published tests of others on large-v3, the model used with Potok, report a word error rate of 8.2 for Romanian, so expect a readable first draft that still needs a proofread. Check special letters and names first.
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
- Two published sources fed this figure, and both are other groups' benchmarks rather than ours.
- Romanian has letters with comma-below and breve marks, and text without them can still look plausible.
- Plain news speech and a family phone call can score very differently.
- A good result on the sample says little about a recording with several overlapping voices.
What a transcript looks like
[00:00] Speaker 1: Să începem ședința. Mai întâi vom analiza rezultatele săptămânii trecute, apoi vom planifica următorii pași.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 |
|---|---|---|---|
| Romanian (Română) | Recommended | word error rate 8.2% (large-v3, FLEURS) Canary-1B-v2 paper, Whale paper | Published tests show a low error rate for this language. |
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 speech with local names. Pick a clip that mentions a city, a street and a person, since proper nouns reveal most.
- Open the bot. Open @potok_now_bot in Telegram and send it as a voice message, an audio file or a video.
- Look at the special letters. Scan for the marked letters and see whether the tool kept them or replaced them with plain ones.
- Compare with a second tool. If you use another service, send the same clip and set the two texts side by side.
- Export a copy. Save the better text as TXT, DOCX, PDF, SRT or VTT. For a long file, up to 2 GB is accepted.
| 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 |
|---|---|---|
| Accepting text that lost its diacritics | It reads fine to a skimmer but is wrong for search and for names. | Search the result for the marked letters. |
| Judging a tidy text without the audio | You may praise a tidy-looking text that does not match what was said. | Always listen while you read. |
| Choosing a sample that is too short | Ten seconds hides most of the problems. | Use half a minute at least. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Is Romanian a recommended language?
It is rated good in the published tests we rely on, though a proofread is still wise.
What does the 8.2 stand for?
It is a word error rate: the share of words wrong in a benchmark by other people.
Will special Romanian letters appear?
Often yes, but check a sample, because dropped marks are a common small defect.
Can I get an English text?
No. The transcript stays in the language of the recording.
What if my clip is large?
Files up to 2 GB are accepted, with an Upload button in the bot's mini app for big ones.
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
- Whale paper, Table 5 (Whisper large-v3 on FLEURS) · 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