Skip to main content

Meeting Transcription

Harmony turns meeting audio into a full, timestamped transcript with speaker labels. You can edit it, search it, add custom vocabulary for better accuracy, and export it in several formats.

What you get​

Every processed meeting has a transcript: who said what and when. Each segment has a timestamp so you can jump to a moment, create clips, or share a specific part. Use search (Ctrl/Cmd + F) inside the transcript to find terms and move between matches. Harmony identifies speakers from meeting attendees and contacts when possible; unknown or unclear speakers may appear as "Speaker X". The ability to correct or reassign speaker labels is not available yet and is under development.

Editing the transcript​

Open the meeting and go to the Transcript tab. Click any text to edit; changes save automatically. Correcting names, companies, and technical terms helps the most—Harmony uses your corrections to improve future transcripts. You can also add terms in Workspace Settings → General → Handbook (product names, jargon, people’s names) so they’re recognized from the start on new recordings.

Speaker labels​

Harmony assigns speaker labels automatically using meeting attendees and contacts. When it can’t identify someone, they may show as "Unknown" or "Speaker X". Correcting or reassigning speakers is not available yet and is under development. Identification works best when audio is clear, there aren’t too many overlapping speakers, and participants are in your contacts.

Language​

Harmony detects the main language automatically. English, Spanish, French, and German are fully supported; others may be available. In meetings with multiple languages, the primary language is transcribed most accurately.

Exporting​

Open the meeting and use Export (or the download icon). You can choose PDF, DOCX, TXT, or JSON and usually control whether to include timestamps, speaker labels, and summary or action items.

Accuracy​

Good audio gives better transcripts. Use a headset or external mic and add your key terms to custom vocabulary. Editing early on teaches Harmony your terminology and improves later meetings. For more, see Transcription quality.

Troubleshooting​

Poor or wrong words — Check that the recording has clear audio. Add terms to custom vocabulary and fix errors in the transcript so Harmony can learn.

Wrong or missing speaker — Identification depends on clear audio and known attendees. Confirm everyone was unmuted and audible. Correcting speaker assignments is not yet available; this is in development.

Missing segments — Check for gaps in the recording (e.g. if recording was paused) or very quiet sections.

Privacy​

Transcripts are encrypted at rest and in transit. Access follows your workspace permissions. Harmony does not use your content for external AI training.