The Potok Telegram bot converts Turkish audio to text when you send the recording. No large-v3 figure was found for Turkish, so published tests of others on the earlier large-v2 model, not our measurements, give a word error rate of 8.4. 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 8.4 is from the earlier large-v2 model, so the current one may differ slightly.
- Turkish has both a dotted and a dotless i, as separate letters, and mixing them up changes the word.
- Words grow long with chained suffixes, so one wrong suffix can look like a different word.
- Vowel harmony means suffix vowels follow the stem, which gives a quick way to spot a wrong ending.
- Turkish uses no grammatical gender, so a pronoun in the text may need your own choice if you later prepare an edit in another style.
What a transcript looks like
[00:00] Speaker 1: Toplantıya başlayalım. Önce geçen haftanın sonuçlarını gözden geçireceğiz, sonra sonraki adımları planlayacağız.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 |
|---|---|---|---|
| Turkish (Türkçe) | Recommended | word error rate 8.4% (large-v2, FLEURS) Whisper paper | Published tests show a low error rate for this language. No large-v3 figure was found; the figure is from the earlier large-v2 model. |
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
- Prepare a clean file. Remove loud intro music if you can, since it can swallow the first words.
- Open the bot. Open @potok_now_bot and attach the recording.
- Big file? Press Upload. The mini app takes up to 2 GB.
- Check the i letters. Search the text for words where the dot may be wrong.
- Read the suffix chains. Pick three long words and compare each ending with the audio.
- Export. Choose DOCX or TXT for edits, SRT or VTT for captions.
| 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 |
|---|---|---|
| Letting the dotless and dotted i mix | Words change meaning. | Search and correct. |
| Ignoring long words | A suffix slip is easy to miss. | Read them aloud. |
| Reading 8.4 as exact | It is an average from others' tests on an earlier model. | Proofread. |
| Using a tool with the wrong language setting | Capital letters can break. | Edit in a Unicode editor. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Why is Turkish scored on large-v2?
No large-v3 figure was found, so the published 8.4 from the earlier model is used.
Do capital and small i match?
In Turkish the dotted and dotless forms are separate letters, so check capitalised words in particular.
What is the maximum file?
The limit is 2 GB per file. For anything too big for a normal chat attachment, use the Upload button in the mini app.
Can I label speakers?
Yes, you can switch on speaker labels, which appear as numbers such as Speaker 1 and never as real names.
Is the text translated?
No. The transcript stays in Turkish, the same language as the recording you send, and it is never converted into another one.
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
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