Captions
for LuumenAI
Check Mirage video jobs, pick a caption style, and render on approval
Connect Captions and Luumen can work with your Mirage account from the terminal. It lists video jobs and their progress, reads error details on a stalled render, and pulls up caption styles with their preview URLs. When it is time to generate speech, animate a portrait, or burn captions onto a finished video, the job is previewed first and started once you approve. Luumen authenticates with an API key.
The Captions toolbox
8 tools: 5 read, 3 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadDownload VideoDownload the MP4 content of a completed video job and return an offloaded file reference.
- ReadGet Caption TemplateRetrieve one caption style by ID, including its name and preview video URL.
- ReadGet Video StatusRetrieve the current state, progress, and error details for a video generation or captioning job.
- ReadList Caption TemplatesReturn one page of available caption styles, including names and preview video URLs.
- ReadList VideosReturn one page of video jobs owned by the connected Mirage account, including each job's status and progress.
- WriteAdd CaptionsStart an asynchronous job that transcribes and renders a selected caption style onto an uploaded or existing completed video. Approval by default
- WriteGenerate SpeechGenerate WAV speech synchronously from text using a known Mirage voice ID and return an offloaded audio file reference. Approval by default
- WriteGenerate VideoStart an asynchronous Mirage Video 1 job that animates a portrait image using speech audio. Approval by default
One prompt, start to finish
What a governed Captions 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 — add captions, generate speech, generate video — is shown as a plan and requires approval by default. 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 Captions — 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 Captions to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.