What is batch transcription? It means transcribing a finished recording after it has been uploaded, rather than while people are still speaking. The system can read the whole file at once, so it can use context from both sides of a word and often returns a more careful text.
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 the whole file exists, the system can look ahead and behind a word, which live systems cannot do.
- Results arrive when processing ends, so batch fits interviews, lectures and meetings you review later.
- One upload can carry a long recording, and the output may include timestamps and speaker labels for the entire file.
- A live feed suits captions during an event; a batch job suits an archive of recordings.
What it looks like
upload town_hall.m4a (finished recording)
status queued -> processing -> done
result town_hall.txt (full transcript)
town_hall.srt (timed subtitles)
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
How is batch different from live transcription?
Live transcription writes text while the speaker talks and must decide quickly. Batch works on a complete file and can take longer to give a steadier text.
When should I choose batch?
Choose it for anything already recorded: interviews, lectures, calls and voice notes. You gain timestamps and labels without needing a stream to be running.
Do I need to wait at my computer?
No. You send the file and come back to the result. A short transcript arrives in the chat and a long one is delivered as a file.
Can a large file be handled as a batch job?
Yes. The Potok bot takes files up to 2 GB, and larger ones go through the Upload button in the bot's mini app.
Is the output different from live?
The text can be cleaner because context is complete. You can also add speaker labels and timestamps, then export TXT, MD, DOCX, PDF, SRT or VTT.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- Speech recognition (Wikipedia), Wikipedia · checked
- Transcription (linguistics) (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