Skip to main content
Connect an AI assistant to Rime’s hosted Model Context Protocol (MCP) server and hear a Rime voice in 60 seconds. Once connected, your assistant can browse the voice catalog, check pronunciation, generate speech samples, and scaffold voice-agent code — all from a conversation.

​
Step 1: Connect

The connector URL is https://mcp.rime.ai. Claude Code: 
claude mcp add --transport http rime https://mcp.rime.ai \
  --header "Authorization: Bearer $RIME_API_KEY"
Claude.ai and Claude Desktop: add https://mcp.rime.ai as a custom connector under Settings → Connectors → Add custom connector. OpenAI Codex: 
codex mcp add rime --url https://mcp.rime.ai \
  --bearer-token-env-var RIME_API_KEY
For other clients — and connecting without an API key — see Connecting.
No key is needed to browse voices or generate integration code. Synthesis and the linguistics tools use your regular Rime API key, sent per request and never stored — see Authentication.

​
Step 2: Hear your first voice

Ask your assistant: 
Play me a sample of a Rime voice.
With no arguments, synthesize_speech plays a short demo in the lyra voice on Coda, Rime’s flagship model.

​
Try more

Find me a warm, conversational voice for a customer support agent.

Which words in this script aren't in Rime's dictionary, and how will the numbers be read aloud?

Generate Pipecat starter code for a voice agent using the astra voice.

​
Next steps

MCP Reference

All six tools, connection setup, authentication, and audio playback

Voices

Browse the full voice catalog across models and languages

Models

Compare models: Coda, Arcana, Mist v3, Mist v2

Streaming TTS

Production streaming over HTTP, WebSockets, or SSE