How to Transcribe a Meeting

Teams use speech-to-text to generate a readable record of discussions, presentations, and team syncs. A transcript makes it simple to search for key decisions and share information with participants who were absent.

Converting audio to text eliminates the need to watch long video recordings simply to find one piece of information.

Note that meeting transcription is used to convert recorded discussions into text. If you instead need to generate spoken narration from a written script, see our guide on text-to-speech for presentations.

Before you can transcribe audio with Konthora, you must prepare the file. Konthora currently accepts media up to 100 MB and up to 10 minutes in duration.

Longer meetings must be divided into shorter recordings before upload. We support audio inputs (MP3, WAV, M4A, AAC) as well as video inputs (MP4, WebM, MOV).

Be aware that audio transcription accuracy is affected by recording quality. Clear audio with minimal overlapping speech will produce the best results.

Konthora provides three timestamp modes: sentence, paragraph, and word-level.

When reviewing a meeting, paragraph mode is often ideal as it groups longer discussion points together for easy reading. Sentence mode offers precise timecode references when you need to jump directly to a specific moment in the original recording. Word-level timestamps provide exact alignment but are less necessary for standard meeting review.

Once the transcript is generated, select an export format that fits your workflow.

For sharing notes or archiving, TXT is the most versatile option. If you are preparing subtitles for a recorded training session, you can export as SRT or VTT. The JSON format is available if you need programmatic access to the text and timestamps.