Read the most recent transcription file from a live-transcribe session.
Finding the latest transcription
The real-time transcript lives in the log file, not the .txt file. The log updates continuously during recording.
# Primary source — real-time log (updates live during recording)
cat /tmp/realtime-transcribe.log 2>/dev/null
# Extract only the spoken text (strip metadata lines)
grep '^\[committed\]' /tmp/realtime-transcribe.log 2>/dev/null | sed 's/^\[committed\] //'
The .txt file (/tmp/transcribe-*.txt) may contain a final dump but does NOT update in real-time. Always prefer the log file.
Check if transcription is still active
if test -f /tmp/realtime-transcribe.pid && kill -0 $(cat /tmp/realtime-transcribe.pid) 2>/dev/null; then
echo "ACTIVE — file is still being updated"
else
echo "FINISHED — file is complete"
fi
Read the file
Use grep to extract committed text from the log, stripping [committed] prefixes. Skip the first JSON status line and [session started] markers.
What to tell the user
- The transcription text
- Whether it's still being updated or finished
- If still active: they can check again later for more content
- If no files found: tell them no transcription has been recorded yet
Working with the transcription
The user may ask to do things with the text beyond just reading it:
- Summarize, translate, extract action items, format, etc.
- The text is available in the main context after reading — proceed with whatever the user asks