What Is Transcription? Definition and Methods

What is transcription? It is writing down spoken words, either by a person or by software. The result is a text version of a recording, such as an interview, a call or a lecture. Manual work is slower, while software gives a quick first draft that still needs reading.

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 trained person listens in short pieces, types and rewinds, so an hour of speech takes far longer than an hour to write down.
Software handles the bulk of the work, but human review is still the way to catch homophones, names and technical terms.
Transcription keeps the language of the speaker; changing it into another language is a separate task.
The same word also means copying music into notes or DNA into RNA, so context decides which meaning is intended.
A recording with one clear voice and little noise is the easiest case, and every added speaker or noise source makes it harder.

What it looks like

// workflow of a transcription job
1. record      meeting.m4a
2. transcribe  meeting.m4a -> meeting.txt
3. proofread   fix names and numbers against the audio
4. export      meeting.docx or meeting.srt

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

Frequently asked questions

What is the difference between transcription and dictation?

Dictation is live: you speak and text appears. Transcription starts from a recording that already exists.

How long does manual transcription take?

Much longer than the recording. It depends on audio quality, number of speakers and how detailed the result must be.

Can software transcribe a video?

Yes. The speech in the audio track is recognised, whatever the video shows. The Potok bot takes video files, voice messages and audio.

What do I get from the bot?

Text in the chat for a short recording, or a file for a long one, with export to TXT, MD, DOCX, PDF, SRT or VTT.

Should I proofread machine transcripts?

Yes. Read the result with the audio, fix names and numbers and check any place where the speakers talk over each other.

Sources

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

Transcription (linguistics) (Wikipedia), Wikipedia · checked 2026-10-18
Speech recognition (Wikipedia), Wikipedia · checked 2026-10-18

Try it on your own recording