AI & Machine Learning

rime.ai

Provides tools for Rime text-to-speech, including listing voices, checking pronunciations, normalizing text, and synthesizing speech audio.

1 endpoint6 known toolsFirst detected September 12, 2026Last detected September 12, 2026

ENDPOINT 1

https://mcp.rime.ai/mcp

No auth detected

MCP server metadata

Name: rime-mcp
Version: 0.1.0

Capabilities

tools.listChangedresources.listChangedprompts.listChanged

Server instructions

Rime is a text-to-speech (TTS) provider for real-time voice agents. This server exposes Rime's voice catalog, linguistics helpers, speech synthesis, and integration scaffolding. Typical workflow: 1. list_voices to find a speaker; get_voice_details for demographics and the exact "lang" value. 2. check_dictionary to see which words are not in Rime's dictionary; normalize_text to preview exactly what the model will speak (numbers, dates, abbreviations). 3. synthesize_speech to generate an audio sample with a chosen speaker and model. 4. generate_integration to emit working LiveKit or Pipecat code for building a voice agent. Notes: - No API key is needed for list_voices, get_voice_details, or generate_integration — users can explore the catalog and get runnable integration code (including keyless LiveKit Inference) before signing up. check_dictionary, normalize_text, and synthesize_speech require a key. - synthesize_speech calls Rime's API and consumes the user's credits; keep sample text short. - Playing audio: UI hosts render an inline player automatically. In a terminal/agent host, take the play URL from the result (structuredContent.audioUrl) and play it with a system audio player (afplay on macOS; ffplay/mpv/aplay/paplay on Linux) — don't just describe it, play it. Pass include_audio=true if the host plays MCP audio blocks natively. - Default model is "coda" (flagship); "mistv3" and "arcana" are alternatives. Speaker names come from list_voices / get_voice_details, never from guesses. - This server does not stream audio and is not for production voice-agent traffic. For that, use generate_integration and point developers to the Rime docs at https://docs.rime.ai. - Some clients surface starter prompts (build_voice_agent, find_a_voice, check_script_pronunciation) that drive these tools; they are optional shortcuts, not required to use any tool.

Known tools 6

list_voices

List Rime's voice catalog as JSON keyed by model and language: { modelId: { langCode: [speaker, ...] } }.

Inferred read-only

get_voice_details

Return detailed metadata for Rime voices (gender, age, accent/dialect, country, genre, model, and language).

Inferred read-only

check_dictionary

Check which words are NOT in Rime's pronunciation dictionary.

Inferred read-only

normalize_text

Preview how Rime normalizes text before synthesis — exactly what the TTS model will speak.

Inferred read-only

synthesize_speech

Generate an MP3 speech sample from text using Rime TTS, rendered in an inline audio player.

Inferred read-only

generate_integration

Generate a ready-to-run code snippet for wiring Rime TTS into a voice agent framework (Pipecat or LiveKit).

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.rime-mcp]
url = "https://mcp.rime.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "rime-mcp": {
      "type": "http",
      "url": "https://mcp.rime.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: rime-mcp
Remote MCP URL: https://mcp.rime.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "rime-mcp": {
      "url": "https://mcp.rime.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "rime-mcp": {
      "type": "http",
      "url": "https://mcp.rime.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "rime-mcp",
  "transport": "streamable-http",
  "url": "https://mcp.rime.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.