The Deepgram connector for Muse

Audio in, transcript out — plus speech back.

The Deepgram connector handles both directions of voice: transcribe prerecorded audio to text, with optional diarization, summaries, topics, and sentiment — and synthesize speech from text. Meetings, interviews, and voice memos become searchable documents.

Diarization is the standout: "who said what" in a multi-speaker recording, labeled and timestamped, ready to quote.

What Muse can do with Deepgram

Transcribe audio files with high accuracy
Diarize speakers: label who said what
Generate summaries, topics, and sentiment from transcripts
Synthesize natural speech from text

Try asking

“Transcribe this interview recording and tell me who said what.”
“Summarize the key points from this hour-long call recording.”
“Turn this announcement into spoken audio.”

Safety notes

Only transcribe audio you have the rights to process.
Transcripts can contain errors, verify quotes before publishing them.
This is a community-built connector. Review its permissions before connecting.

How to connect Deepgram

Open the Muse app, go to settings, and find connectors. Link your Deepgram account with the standard sign-in — Muse never sees your password. Once linked, the connector is available across your conversations. You can scope it to read-only or disconnect it entirely at any time from the same screen.

Questions

What audio formats does it accept?

Deepgram handles common formats like MP3, WAV, and M4A. If yours is unusual, convert first.

How accurate is the transcription?

Very good on clear audio, weaker on crosstalk and heavy accents. Diarization helps, but always spot-check consequential quotes.

Related connectors

Connector status last checked October 13, 2026. The authoritative, current list lives in the Muse app's settings, under connectors. Back to the full directory →