Finnish audio can be converted to text by sending it to the Potok bot on Telegram. Published tests of others on large-v3, not our measurements, report a word error rate of 7.7 for Finnish. Files up to 2 GB are accepted, and the transcript stays in Finnish.
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
- Finnish uses long words with many endings, so a single wrong ending counts as a whole wrong word in the metric.
- Numbers and place names deserve a second look, because they have many forms.
- Spoken Finnish often differs from the written standard in everyday talk.
- Export as DOCX, TXT, PDF, MD, SRT or VTT.
What a transcript looks like
[00:00] Speaker 1: Aloitetaan kokous. Ensin käymme läpi viime viikon tulokset ja sitten suunnittelemme seuraavat vaiheet.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 |
|---|---|---|---|
| Finnish (Suomi) | Recommended | word error rate 7.7% (large-v3, FLEURS) Canary-1B-v2 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
- Open the bot. Open @potok_now_bot in Telegram.
- Send the recording. Attach audio or video, or paste a YouTube link. Files up to 2 GB; use the Upload button for big ones.
- Look at word endings. A case ending can differ by one letter. Compare suspect words with the audio.
- Check numbers. Spoken numbers may appear as digits or words. Make them consistent in your edit.
- Fix the names first. Surnames and towns carry endings that change the form. Search for each name once and correct every occurrence in one pass.
- Export. Choose a format and save it, SRT if the text becomes subtitles.
| 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 |
|---|---|---|
| Judging only by whole words | One wrong ending makes a long word count as wrong. | Read the whole sentence before deciding the text is bad. |
| Mixing number styles | Digits and words get mixed in the same page. | Pick one style when you edit. |
| Skipping place names | Place names appear in many case forms. | Check them in a map or document. |
| Sending a very noisy field recording | Wind hides the soft sounds. | Use a wind cover or record indoors. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
How good is Finnish?
The published word error rate is 7.7 on large-v3, which is good, though it is a figure from tests of others.
Why can a word error be harsh in Finnish?
Words are long and carry endings, so one wrong letter marks the whole word wrong.
Can I upload a lecture video?
Yes, a lecture or interview video is read like audio, within the 2 GB file limit of the bot.
Is the text translated?
No, the text stays in Finnish, which is the language of the recording you sent.
Can I mark who is speaking?
Yes, switch on numbered speaker labels before you send the file, and each line gets a number.
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
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