Potok can turn Arabic voice messages, audio and video into text through a Telegram bot, but with a caution. Published tests of the large-v2 model report a word error rate of 16 for Arabic, and dialect speech scores worse than Modern Standard Arabic. 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 16 is a word error rate from published tests of the earlier large-v2 model, not a measurement we made.
- A third-party average for the turbo variant was 10.57, so the published numbers for Arabic do not agree on one value.
- Spoken dialects differ a lot from Modern Standard Arabic, and error rates are higher on dialect speech.
- Arabic runs right to left, so open the exported file in an editor that handles that direction.
What a transcript looks like
[00:00] Speaker 1: لنبدأ الاجتماع. أولاً سنراجع نتائج الأسبوع الماضي، ثم نخطط للخطوات التالية.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 |
|---|---|---|---|
| Arabic (العربية) | Use with care | word error rate 16% (large-v2, FLEURS) Whisper paper, TheWhisper benchmark | Published tests show a higher error rate for this language. Check a short sample first and plan to proofread. The figure is from the earlier large-v2 model and a third-party turbo average was 10.57. Dialects differ a lot from Modern Standard Arabic, and error rates are higher on dialect speech. |
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
- Decide which Arabic you have. News, lectures and prepared speech are close to the standard form. Street conversation and family calls are dialect, so expect more corrections.
- Start the bot. Open @potok_now_bot in Telegram and send the voice message, audio, video or YouTube link.
- Use Upload for big files. Anything up to 2 GB is accepted; for a long recording use the Upload button of the bot's mini app.
- Read a short stretch first. Compare the first minute with what you hear before you trust a long transcript, especially for dialect.
- Export. Choose TXT or DOCX for reading, SRT or VTT for subtitles. Keep timestamps on if you plan to check passages against the audio.
| 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 |
|---|---|---|
| Treating one score as proof for every Arabic dialect | Dialect recordings produce clearly more errors than formal speech. | Test a short clip from your own speaker before sending hours of audio. |
| Reading the exported file in a left-to-right editor | Punctuation and digits jump to the wrong side of a line and the text looks broken. | Open it in a word processor with right-to-left support. |
| Quoting the 16 as our own result | Readers assume the figure was measured on your audio. | Say it comes from published third-party tests. |
| Expecting an English text back | The transcript stays Arabic because the bot does not translate. | Translate the finished text in a separate step. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Why does the Arabic page carry a caution?
Published error rates for Arabic are higher than for the recommended languages, and they rise further on dialect speech, so the result needs a careful read.
Does it understand Egyptian, Gulf or Levantine speech?
The published tests do not break results down by dialect, only noting that dialects differ a lot from Modern Standard Arabic. Try a short sample first.
Can I send an Arabic video or a YouTube link?
Yes. The bot reads audio and video files and accepts YouTube links, within the 2 GB file limit.
Will short vowels and diacritics be written?
Do not count on it. Ordinary Arabic text often leaves them out, and you should add any marks you need by hand.
Can I get the transcript in English?
No. The transcript stays in the language of the recording, and the bot does not translate it.
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
- Whisper paper, Table 13 (large-v2 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