Deepgram
for LuumenAI

Check Deepgram usage, models, and transcripts from the terminal

Connect Deepgram with an API key and ask about it in plain language. Pull project usage with DEEPGRAM_GET_PROJECT_USAGE_SUMMARY when a bill looks off, check which models are available with DEEPGRAM_GET_MODELS, review scopes on a project, or run a file through DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED. Every tool here is read-only, so answers come back right away.

Book a DemoDownload Luumen

The Deepgram toolbox

8 tools, all read-only. They answer instantly, and every call is logged.

  • ReadGet Model by IDRetrieve metadata for a specific Deepgram model by its UUID.
  • ReadGet Public ModelsRetrieve metadata on all public Deepgram models (speech-to-text and text-to-speech).
  • ReadList Deepgram ProjectsList all Deepgram projects.
  • ReadGet Project Usage SummaryRetrieves aggregated usage statistics for a Deepgram project including total audio duration, billable duration, number of requests, channels processed, and confidence/relevance scores.
  • ReadList Project ScopesList all scopes for a specified Deepgram project.
  • ReadList Think ModelsList available think models for AI agent processing and voice agent configuration.
  • ReadTranscribe Pre-recorded AudioTranscribe pre-recorded audio files into text.
  • ReadText-to-Speech (REST)Convert text into natural-sounding speech.

Questions

How does LuumenAI connect to Deepgram?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

Can LuumenAI change things in Deepgram on its own?

No. Every one of the 8 tools LuumenAI has for Deepgram is read-only, so it can answer questions from Deepgram but cannot change anything in it. Reads are not gated — they answer immediately, and each one is recorded on the audit trail with the actor and the result.

Who gets access to the integration?

You decide. Access is granted per agent, skill, and team, and per environment — production is not staging.

Is there an audit trail?

Every call to Deepgram is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.

All integrations
Adobe Marketing Agent MCPAdobe Experience Platform context, sandbox switches, and async task statusAffindaRead parsed documents, collections, and annotations — change them with approvalAgent MailGive the agent its own mailbox for reading threads and sending updatesAI/ML APIInspect assistants, threads, and runs — and change them as approved steps

Put Deepgram to work with Luumen

Connect in minutes. Every action scoped, approved, and audited from day one.

Book a DemoDownload Luumen