Gladia
for LuumenAI
Transcribe incident calls and check job status without leaving the terminal
Connect Gladia and the agent can see your transcription work from the terminal. List pre-recorded jobs, pull the status and text of a specific job, and check live sessions still running. When you need a new transcript, it can start a pre-recorded job or open a live session as an approved step. Authentication is by API key.
The Gladia toolbox
9 tools: 4 read, 5 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadGet live transcription resultRetrieve metadata and results of a live transcription job.
- ReadGet Pre-recorded JobRetrieve a pre-recorded transcription job's metadata, status, and results by ID.
- ReadList live transcription jobsList live transcription jobs.
- ReadList Pre-Recorded JobsList all pre-recorded transcription jobs matching the query parameters.
- WriteDelete Live SessionDelete a live transcription session and all its associated data (audio file, transcription). Approval by default
- WriteDelete Pre-recorded JobDelete a pre-recorded transcription job and all its associated data (audio file, transcription). Approval by default
- WriteInitiate Live Transcription SessionInitiates a live (real-time) transcription session with Gladia's API. Approval by default
- WriteInitiate Pre-Recorded TranscriptionInitiate a pre-recorded transcription job. Approval by default
- WriteUpload Audio/Video FileUpload an audio or video file to Gladia for speech-to-text transcription. Approval by default
One prompt, start to finish
What a governed Gladia run looks like inside Luumen.
Questions
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — delete live session, delete pre-recorded job, initiate live transcription session, initiate pre-recorded transcription, and more — is shown as a plan and requires approval by default, including the 2 actions classified as destructive. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to Gladia — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Often connected alongside
All integrations
Adobe Marketing Agent MCPAdobe Experience Platform context, sandbox switches, and async task status
AffindaRead parsed documents, collections, and annotations — change them with approval
Agent MailGive the agent its own mailbox for reading threads and sending updates
AI/ML APIInspect assistants, threads, and runs — and change them as approved stepsPut Gladia to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.