Resemble AI TTS Server

Example Use Cases

• 1

  Generate spoken audio from text using Resemble AI voices and return results as files or base64 payloads.

• 2

  Enumerate available voice models (IDs, names, languages, accents) to present selection options or programmatically pick voices.

• 3

  An MCP-compatible bridge (SSE or StdIO) to integrate Resemble TTS into Claude Desktop or Cursor workflows while keeping the service locally managed.

Description

This repository provides a Model Context Protocol (MCP) server that lets agents generate voice audio via the Resemble AI API. It supports multiple transports (SSE network-based Server-Sent Events or StdIO subprocess communication), returns audio as files or base64, and includes tools to list voices and generate TTS. The server is useful for integrating Resemble's voices into agent workflows while running a local or self-hosted bridge for Claude Desktop and Cursor.