Gradium
for LuumenAI
Check voice usage and credits, and edit pronunciation dictionaries with approval.
Connect Gradium and your team can check credit balance, usage totals, and voice metadata without opening another console. Pronunciation dictionaries are readable rule by rule, so you can see exactly how a term is spoken today. Edits to those dictionaries are previewed and held for approval before they run. Luumen authenticates with an API key.
The Gradium toolbox
9 tools: 6 read, 3 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadGet CreditsGet the connected Gradium subscription's current credit balance and billing-period metadata.
- ReadGet Pronunciation DictionaryRetrieve one pronunciation dictionary and its complete rewrite rule set by UID.
- ReadGet Usage SummaryRetrieve aggregate Gradium session, message, text, audio-duration, and consumed-credit usage totals.
- ReadGet VoiceRetrieve metadata for one Gradium catalog or custom voice by its UID.
- ReadList Pronunciation DictionariesList pronunciation dictionaries for the connected organization, optionally filtered by language.
- ReadList VoicesList custom voices and, by default, Gradium's public voice catalog, returning voice IDs and metadata for later selection.
- WriteCreate Pronunciation DictionaryCreate a language-specific pronunciation dictionary with optional rewrite rules. Approval by default
- WriteDelete Pronunciation DictionaryPermanently delete one pronunciation dictionary by UID. Approval by default
- WriteUpdate Pronunciation DictionaryUpdate pronunciation dictionary metadata and optionally replace its complete rewrite rule set. Approval by default
One prompt, start to finish
What a governed Gradium 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 — create pronunciation dictionary, delete pronunciation dictionary, update pronunciation dictionary — is shown as a plan and requires approval by default, including the 1 action 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 Gradium — 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 Gradium to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.