Read voice models, agents, and credit. Change agent config as an approved step.
Connect Fish Audio with an API key and Luumen can read your workspace directly: which voice models are trained and usable, how your agents are configured, what sessions they have handled, and how much package allowance and paid credit remain. Changes — creating an agent, updating its draft prompt or voice, synthesizing speech — are previewed first and go through approval before they run.
10 tools: 6 read, 4 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Fish Audio run looks like inside Luumen.
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 — configure agent, create agent, delete agent, synthesize speech — 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 Fish Audio — 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.
Connect in minutes. Every action scoped, approved, and audited from day one.