Give a character one voice, forever

Store a character sheet, a bio and a provider voice id on one avatar, and reuse it for every script.

Set up a GroundSlate avatar for the mascot: a plush build, pink body, white moustache, antennae, red jacket, who talks warm and unhurried and slightly conspiratorial. Attach my ElevenLabs voice <<YOUR ELEVENLABS VOICE ID>> to him, then read the whole thing back to me.

Paste it into any MCP client

Works with

ElevenLabs, or any voice or music model: Generates the audio, outside GroundSlate. Your agent generates it through its own connection to the provider, an MCP server or an API key, and hands the file back. It stores the voice id against a character and mixes, ducks and lays whatever your agent brings back. Most work needs no provider at all: GroundSlate speaks scripts locally in a designed or stock voice, and writes instrumental beds and sound effects locally too. A provider is for a specific voice you own, or a catalogue track you want by name.

Everything in <<double brackets>> is yours. Fill it in before you paste.

GroundSlate stores the voice id on the avatar but does not make the audio. Your agent makes it through its own ElevenLabs connection, an MCP server or your API key, and hands the file back.
An avatar is a character, not a person. It has nothing to do with face recognition.