Opus to text

By the Potok teamUpdated ~2 min read

To convert Opus audio to text, send the file to the Potok bot on Telegram and read the result in the chat. Voice messages from chat apps are often Opus, and you can send them without conversion. Files up to 2 GB are accepted, and a long transcript arrives as a file.

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

  • Opus is an audio codec designed for speech and music over the internet, so it keeps voices clear at small sizes.
  • WhatsApp voice messages use Opus. When you export one from the chat, you get an .opus or .ogg file.
  • An Opus file is small, so even a long voice note is far below the size limit.
  • A codec is not a file type: Opus audio can sit inside OGG, WebM or other containers.

How to do it

  1. Export the voice message. In the chat app, share the voice message to Telegram, or save it as a file. The ending is often .opus or .ogg.
  2. Open the bot. Open @potok_now_bot in Telegram.
  3. Send the audio. Forward the shared message or attach the file as a document. A very large file, up to 2 GB, goes through the Upload button.
  4. Choose labels for a group chat. If several people sent voice notes, collect them in one file and switch speaker labels on.
  5. Wait and export. Read the text in the chat, or take the file for a long result. Export TXT, MD, DOCX, PDF, SRT or VTT.

What the result looks like

Example: a voice note from a messenger as a transcript

[00:00] Speaker 1: Hi, it is Nora. The delivery came, but one box is missing.

[00:06] Speaker 1: Can you check the order number and call me tonight?

Sample text written by us to show the layout of a transcript. It is not the output of the recognition engine and not a real recording.

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
Recording the playback of a voice message with a second phoneRoom noise and an extra compression step damage the speech.Share the original message instead of re-recording it.
Converting Opus to a low-bitrate MP3 firstA second lossy step removes detail the recogniser needs, and quiet words come out wrong.Send the Opus file as it is.
Treating a forwarded note as a different recordingThe same message gets transcribed twice, and the texts differ slightly, which causes confusion.Keep one version and note where it came from.
Using the transcript as proof of what someone saidA voice note may contain a mumbled word that the text records as something else.Listen to the passage again before quoting it.

More

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

Frequently asked questions

What is Opus?

Opus is an audio codec made for speech and music over the internet. It is widely used in voice messages.

Can I send a WhatsApp voice message to the bot?

Yes. Share it to Telegram or save it as a file, then send it to the bot.

Do I have to turn it into MP3?

No. Conversion adds another compression step and is not needed for the bot.

Why does an Opus file look like OGG?

Opus audio is often stored inside an OGG container, so the file ending can be .ogg.

Is the transcript translated?

No. The text stays in the language of the voice note.

Sources

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

  1. Opus audio format (Wikipedia), Wikipedia · checked
  2. WhatsApp (Wikipedia), Wikipedia · 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