Find a Typecast voice, then generate the audio as an approved step.
Connect Typecast and Luumen can browse the voices your account can use, check a voice's supported models and emotions, and see where your plan stands on credits and concurrency. When you ask for audio — a status announcement, an IVR line, a narration track — the agent picks the voice, shows you the text and settings, and generates the file after you approve.
7 tools: 4 read, 3 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Typecast 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 — compose speech, generate speech, generate speech with timestamps — 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 Typecast — 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.