Skip to main content
HTTP API connector An HTTP API described by an OpenAPI spec, not an MCP server. Calls go to your ElevenLabs address (https://{baseUrl}, filled in when connecting) and carry the credential the connect dialog asks for.

​
What the skill can do

API connector: 11 actions, as they appear in the skill panel. 7 of them create, change or delete something in ElevenLabs; mark those under These actions need approval when you add the skill to an agent.
  • Text to speech service (5): Eleven Labs Text To Speech Stream Text With Timestamps, Eleven Labs Text To Speech Generate Audio With Timestamps, Eleven Labs Text To Speech Convert Text To Audio, Eleven Labs Text To Speech Stream Text To Audio, Eleven Labs Voice Management List All Voices
  • History management (3): Eleven Labs History Manage Retrieve All Audio Records, Eleven Labs History Manage Delete Specific Audio Record, Eleven Labs History Manage Retrieve Specific Audio Record
  • Speech transformation (2): Eleven Labs Speech Transform Convert Audio To Target Voice, Eleven Labs Speech Transform Stream Audio To Target Voice
  • Voice management (1): Eleven Labs Voice Management Retrieve Voice Settings

​
Connect ElevenLabs

In Xpander Chat, open the agent’s settings, click Add skill, and search for ElevenLabs. The connect dialog asks for a connection name and whether the connection is for the Organization (one shared account) or Personal (your own account, so the agent acts with your permissions where systems allow). On an agent other people use, a personal connection runs their requests as you unless the binding requires each person’s own sign-in; see whose credential a shared agent uses. The dialog shows the credential this skill needs and where it goes; the value is stored in the vault and attached at the moment of use. Calls go to https://{baseUrl}.

​
Give an agent the ElevenLabs skill

Once ElevenLabs is connected, any agent you can edit may be given the skill: open the agent’s settings, click Add skill, and choose ElevenLabs. Enable only the action groups the agent needs, and mark the actions that should wait for a named person’s sign-off under These actions need approval. Which skills exist for your organization, and who may add them, is decided by your admins; see Skills.