Rime MCP — text-to-speech tools for AI agents
================================================

This is a Model Context Protocol (MCP) server, not a website.

  Endpoint    https://mcp.rime.ai   (Streamable HTTP, stateless; /mcp is an alias)
  Health      https://mcp.rime.ai/health
  Quickstart  https://docs.rime.ai/docs/mcp
  Docs        https://docs.rime.ai

Connect
  Claude.ai/Desktop  Settings > Connectors > Add custom connector > https://mcp.rime.ai
  Claude Code        claude mcp add --transport http rime https://mcp.rime.ai
  ChatGPT desktop    Settings > MCP servers > Add server > Streamable HTTP > https://mcp.rime.ai
  OpenAI Codex       codex mcp add rime --url https://mcp.rime.ai --bearer-token-env-var RIME_API_KEY
  Other clients      {"mcpServers":{"rime":{"url":"https://mcp.rime.ai"}}}

Auth
  Most tools need a Rime API key (https://app.rime.ai/tokens).
  Send it as:  Authorization: Bearer <key>
  No key needed for list_voices, get_voice_details, generate_integration.

Tools
  list_voices            Browse the voice catalog by model and language
  get_voice_details      Voice demographics + the exact lang value for synthesis
  check_dictionary       Find words not in Rime's pronunciation dictionary (API key required)
  normalize_text         Preview exactly what the TTS model will speak (API key required)
  synthesize_speech      Generate speech (MP3) with a chosen voice and model (API key required)
  generate_integration   Working Pipecat / LiveKit voice-agent code

Speak MCP directly (JSON-RPC over POST):
curl -s https://mcp.rime.ai \
  -X POST \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'