Finnish speech to text through Potok is a recommended language. Published tests of large-v3 report a word error rate of 7.7, measured by others, not by us. Finnish builds long words from endings, so one wrong letter counts as a whole wrong word.
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
- Because Finnish words carry many endings, a word error rate punishes a small slip heavily.
- 7.7 is a single published reading and your clip may land above or below it.
- Spoken Finnish and written Finnish differ, and the text follows what is said, so colloquial forms may appear.
- Speaker labels are numbered, not named.
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
- Check the style. If the speaker uses casual talk, expect colloquial spellings in the text.
- Open the bot. Go to @potok_now_bot and attach audio, video or a voice note.
- Read for endings. Case endings are where small errors appear. Compare a few sentences with the audio.
- Send big files via Upload. The limit is 2 GB.
- Export. Use DOCX for editing and SRT for captions.
- Keep the original audio. Replaying a doubtful ending against the source is the quickest way to settle a spelling.
| 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 |
|---|---|---|
| Counting a wrong ending as a small error | In a word-based score it is a full miss. | Judge by meaning, not by the number. |
| Expecting formal spelling from casual speech | The text follows what is said. | Edit the text if you need formal form. |
| Searching for a short stem in the output | Inflected forms may not match. | Search for the shorter stem. |
| Quoting 7.7 as our test | It is a published result. | Cite as published by others. |
| Judging quality from the opening sentence | Long inflected words may go wrong later in the recording. | Sample a stretch from the middle. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
What is the Finnish score?
A published word error rate of 7.7 for large-v3, measured by others and not by us.
Why do long words matter?
A word error rate marks any word with a wrong letter as an error, and Finnish words are long and inflected.
Is colloquial speech written as it sounds?
Often yes, so expect spoken forms rather than the formal standard in the text.
Can I upload large files?
Yes, up to 2 GB, and the Upload button of the mini app handles the biggest ones.
Is the transcript put into English?
No. It stays in Finnish because the bot does not translate transcripts.
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