Transcribe Audio

Location on ribbon: Tab DVD Addin → Group File and Print → Menu File Tools

Command ID: btnTranscribeAudio

License required

This command needs an active DVDAddin account (Standard or PRO). It is fully available during the Trial period.

What it does

Sends an audio recording to Gemini AI for transcription and writes the resulting text straight into the active cell.

It is the fast way to get minutes out of a recording: a Monday site coordination meeting, a discussion with the supervision consultant on site, or a voice memo taken while inspecting an activity. Instead of replaying and typing, you start from a text draft.

How to use

1. Click the cell that should receive the text — the result lands in whatever cell is active.
2. Go to tab DVD Addin → group File and Print → menu File Tools → click Transcribe Audio.
3. The "Select an audio file to transcribe" dialog opens, filtered to *.wav; *.mp3; *.flac; *.ogg; *.aac → pick the recording → Open.
4. The add-in uploads the file to Gemini and waits for the answer. Excel is unresponsive while a long file is processed — that is expected.
5. When it returns, the full transcript is written into the active cell.

Example

After Monday's site coordination meeting you have Coordination_2026-05-11.mp3, twelve minutes long.

Select cell B2 on the Meeting Minutes sheet, run the command, pick the file → the discussion (piling progress, access blocked on plot C, extra manpower request) appears as one text block in B2. From there you split it into points and edit it into the formal minutes.

Notes

• Requires an internet connection and a Gemini API key configured in Preferences; without either, the cell receives an error message instead of a transcript.
• The recording is uploaded to an external AI service — do not use it for confidential meetings or sensitive project information.
• The result overwrites the active cell and cannot be undone with Ctrl+Z, so aim at an empty cell.
• The entire transcript sits in one cell — turn on Wrap Text and raise the row height to read it, or copy it into Word.
• Only .wav, .mp3, .flac, .ogg and .aac are accepted; .m4a recordings from phones must be converted first.
• Longer files take longer and consume more API quota; split long recordings into segments.

Related

• OCR — same AI family, but reads text from images and PDFs instead of audio.
• Screen Clip OCR — grab text quickly from a region of the screen.
• AI Assistant — clean up and summarise the transcript you just produced.
• Translate — translate the minutes for a foreign consultant.