Cartesia (Voice AI) MCP Server for Claude CodeGive Claude Code instant access to 20 tools to Clone Voice, Create Pronunciation Dict, Delete Pronunciation Dict, and more

Connect Cartesia to your AI agent to unlock high-performance voice synthesis and speech recognition. Cartesia's Sonic models provide industry-leading latency and quality for real-time applications.

Claude Code registers Cartesia (Voice AI) as an MCP server in a single terminal command. Once connected, Claude Code discovers all 20 tools at runtime and can call them headlessly. ideal for CI/CD pipelines, cron jobs, and automated workflows where Cartesia (Voice AI) data drives decisions without human intervention.

What you can do

• Text-to-Speech (TTS) — Generate high-fidelity audio bytes or stream via SSE using models like Sonic 3.5 and Sonic 3.
• Speech-to-Text (STT) — Transcribe audio files into text using the Ink Whisper model with multi-language support.
• Voice Cloning — Create custom voice models from as little as 5 seconds of audio input.
• Voice Management — List, retrieve, and update voices, or use the Voice Changer to transform existing audio.
• Pronunciation Control — Manage custom pronunciation dictionaries for specialized terminology or accents.
• Agent Orchestration — List and manage AI agents and monitor call logs and usage credits.

The Cartesia (Voice AI) MCP Server exposes 20 tools through the Vinkius. Connect it to Claude Code in under two minutes — credentials fully managed, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.