Malay speech to text in Potok is a recommended language, with a published word error rate of 8.7. The figure is from the earlier large-v2 model, because no large-v3 result was found. It is a result from other people's tests, not our measurement. Send voice, audio or video to the bot.
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 8.7 figure comes from the older large-v2 model, so a newer model may score differently on the same speech.
- Malay and Indonesian share much vocabulary, which is a reason to name the language of your clip when you are unsure.
- Everyday Malay speech often includes English words, and those can be spelled in either language in the output.
- Malay is written in the Latin script, so the exported text needs no special font.
What a transcript looks like
[00:00] Speaker 1: Mari kita mulakan mesyuarat. Pertama, kita semak keputusan minggu lalu, kemudian kita rancang langkah seterusnya.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 |
|---|---|---|---|
| Malay (Bahasa Melayu) | Recommended | word error rate 8.7% (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
- Pick the recording. Meeting audio, a class or a voice note all work. A single clear speaker gives the neatest start.
- Open the chat. Tap through to @potok_now_bot and send the file, a forwarded voice message, or a YouTube link.
- Mind the file size. Anything up to 2 GB can go in. Use the Upload button of the mini app when the file is large.
- Wait for the text. A short transcript is posted in the chat and a longer one arrives as a file.
- Scan English insertions. Look at brand names, technical terms and quoted phrases, where spelling choices differ.
- Export. Choose TXT, MD, DOCX, PDF, SRT or VTT depending on whether you need notes or 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 |
|---|---|---|
| Quoting 8.7 as a result for the latest model | It was published for large-v2. | State the model when you cite it. |
| Recording in a busy market or street | Background noise adds wrong words. | Choose a calmer place for the microphone. |
| Assuming Malay and Indonesian clips behave the same | Vocabulary overlaps but is not identical. | Check unfamiliar words in your own file. |
| Skipping timestamps for a video project | You lose the link between text and picture. | Turn timestamps on and export SRT or VTT. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
What is the published score for Malay?
A word error rate of 8.7 for the large-v2 model, as reported in published tests of others.
Why not large-v3?
No large-v3 figure for Malay was found, so we show the earlier model's number rather than guess.
Do mixed Malay and English clips work?
English words are usually written, but their spelling should be checked in the output.
Does the bot change the transcript into English?
No. The text stays in the language of the recording.
Can I send a video?
Yes, the bot takes video files and YouTube links as well as audio.
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