Tagalog transcription at Potok is borderline: the published word error rate is 13.8, from the earlier large-v2 model, close to the 15 line we use. Expect to proofread. Audio and video up to 2 GB are accepted in Telegram, and the text comes back in Tagalog.
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 13.8 is a word error rate from published tests of large-v2, not our measurement, and no large-v3 figure was found.
- It sits close to the 15 line, so a noisy recording can tip it into the cautioned range.
- Everyday speech often mixes in English words, and they may be spelled either way in the result.
- Speaker labels are numbered, and timestamps are optional.
What a transcript looks like
[00:00] Speaker 1: Simulan na natin ang pulong. Una, susuriin natin ang mga resulta noong nakaraang linggo, pagkatapos ay magpaplano tayo ng mga susunod na hakbang.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 |
|---|---|---|---|
| Tagalog | Recommended, borderline | word error rate 13.8% (large-v2, FLEURS) Whisper paper | Published tests show an error rate close to our 15% line. Check a short sample first. No large-v3 figure was found; the figure is from the earlier large-v2 model and sits close to the 15% line. |
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
- Judge with a clip first. Send one minute to @potok_now_bot and see how your speakers fare.
- Send the full recording. Up to 2 GB is accepted, with the mini app's Upload button for the biggest files.
- Turn on timestamps. They make it faster to find the lines that need a second listen.
- Review the mixed-language passages. Compare them with the audio and settle on one spelling.
- Export. TXT, MD, DOCX, PDF, SRT or VTT.
| 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 borderline as good | More mistakes than in the recommended languages remain in the text. | Plan a full read-through. |
| Forgetting that the figure is from large-v2 | It may not describe the current model. | Cite the model name. |
| Letting English phrases pass unchecked | Borrowed words are a likely place for spelling drift. | Settle on a style and apply it. |
| Publishing subtitles unedited | Viewers see every error. | Edit the SRT before release. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Is Tagalog transcription reliable?
It is borderline. The published error rate of 13.8 is close to the 15 line, so read the text before using it.
Why is only a large-v2 number cited?
No large-v3 figure was found, so the earlier model's result is the one available.
How are English words handled?
They appear where they were spoken, and spelling may vary, so check them.
What exports can I choose?
You can save TXT, MD, DOCX and PDF for reading, or SRT and VTT for captions.
Is there an English version of the text?
No. The transcript stays in Tagalog, with any English words left where they were spoken.
Can I send a long meeting?
Yes, up to 2 GB, and the Upload button of the mini app helps with very large files.
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
- Whisper speech recognition system (Wikipedia), Wikipedia · 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