Server URL
https://mcp.rime.ai/mcp serve the MCP endpoint — use whichever your client expects. See Connecting for client-by-client setup.
Tools
list_voices
List the voice catalog, filterable by model and language. No API key.
get_voice_details
Voice metadata: gender, age, accent, country, and the
lang value for synthesis. No API key.check_dictionary
Find words not in Rime’s pronunciation dictionary.
normalize_text
Preview exactly what the TTS model will speak.
synthesize_speech
Generate an MP3 sample with an inline audio player.
generate_integration
Emit ready-to-run Pipecat or LiveKit code. No API key.
Learn more
Connecting
Set up Claude Code, Claude.ai, OpenAI Codex, and other MCP clients
Authentication
Per-request API keys, accepted headers, and which tools work without one
Playing audio
How synthesized samples reach your speakers in UI and terminal hosts
Starter prompts
Optional shortcuts surfaced by clients that support MCP prompts
The MCP server is built for exploration and prototyping — it generates complete audio samples rather than streaming. For production voice agents, use the streaming APIs directly, or ask
generate_integration for working Pipecat or LiveKit starter code.