Bulgarian transcription: audio and video to text

By the Potok teamUpdated ~2 min read

Yes, Potok transcribes Bulgarian recordings in Telegram and returns the text in the Cyrillic alphabet. Published tests of the large-v3 model show a word error rate of 12.86 for Bulgarian, a good result on our list. You can send voice notes, audio, video or files up to 2 GB.

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

  • A word error rate of 12.86 for Bulgarian comes from a published paper on the large-v3 model, not from our own testing.
  • The Bulgarian text comes back in Cyrillic, so search it with Cyrillic keywords rather than Latin spellings.
  • Names of people and places are the usual weak spot, so compare them with a trusted spelling.
  • The transcript is not translated into another language.

What a transcript looks like

Sample sentence in Bulgarian
[00:00] Speaker 1: Да започнем срещата. Първо ще прегледаме резултатите от миналата седмица, а след това ще планираме следващите стъпки.

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

Quality for this language
LanguageVerdictPublished resultNotes
Bulgarian (Български)Recommendedword error rate 12.86% (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

  1. Send the recording. In @potok_now_bot attach the voice message, audio, video or paste a YouTube link.
  2. Mind the size. The limit is 2 GB per file. A long lecture can go through the Upload button in the bot's mini app.
  3. Turn on labels for conversations. Speaker labels and timestamps are optional. Enable them for interviews or meetings with several voices.
  4. Proofread the proper nouns. Scan the Bulgarian text for surnames, town names and brand names first, since those are most likely to be spelled differently.
  5. Export what you need. Download TXT, MD, DOCX or PDF to share, or SRT or VTT to subtitle a clip.
What Potok can do
FeatureDetails
Where it worksTelegram bot @potok_now_bot; large files go through the bot's mini app
File sizeUp to 2 GB
ExportTXT, MD, DOCX, PDF, SRT, VTT
Speakers and timeSpeaker labels and timestamps can be switched on
LanguagesAbout 30 languages with good published results; a few more with warnings
TranslationThe transcript is not translated into another language
DictationA separate Potok desktop app lets you dictate text into any program; it recognises Russian speech

Common mistakes

Common mistakes and how to fix them
MistakeWhat happensFix
Searching the transcript in Latin lettersNothing matches because the text is written in Cyrillic.Switch the keyboard layout or search with Cyrillic terms.
Skipping a check of namesA wrong surname can reach a published document unnoticed.Compare names with an official source before use.
Sending a call with heavy background noiseNoise raises the error rate for Bulgarian as in any language.Send the cleanest copy you have, recorded near the speaker.

More

See the full list of languages, the tools and the glossary.

Frequently asked questions

How accurate is Bulgarian transcription?

Published tests of the large-v3 model give a word error rate of 12.86 for Bulgarian. That is another group's figure, not our measurement, and your audio may differ.

Does the bot return Cyrillic text?

Yes. The Bulgarian transcript is written in the Cyrillic alphabet, and exports keep that text as it is.

Can I send a Bulgarian video from YouTube?

Yes. Paste the YouTube link into the chat and the bot transcribes the speech, as long as the content fits the size limits.

Are speakers named in the result?

No. If you switch labels on you get numbers such as Speaker 1, and you can rename them in the exported file.

Is the Bulgarian text translated for me?

No. The transcript stays Bulgarian, since the bot does not translate transcripts into other languages.

Sources

Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.

  1. FLEURS speech dataset (Google, Hugging Face), Hugging Face · checked
  2. Whisper speech recognition system (Wikipedia), Wikipedia · checked
  3. 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