{"apiVersion":"v1","directorySlug":"rime-mcp-64636189bd","title":"Rime | Conversational Voice AI","description":"AI voice models built for real-time conversations. 600+ voices, 50+ languages, sub-100ms latency. Trusted by global enterprise.","pageUrl":"https://www.mcpbundles.com/skills/rime-mcp-64636189bd","connectPath":"importable","connectAction":"import_server","catalogListing":false,"bundleSlug":null,"listingKind":"remote_mcp","kind":"provider","transportUrl":"https://mcp.rime.ai/mcp","hostedMcpUrl":null,"toolCount":6,"toolInventoryStatus":"observed","refreshedAt":"2026-11-03T13:26:00.516172+00:00","registryName":"ai.rime/rime-mcp-64636189bd","registryVersion":"2026.11.3","registryEligible":true,"tools":[{"name":"list_voices","description":"List Rime's voice catalog as JSON keyed by model and language: { modelId: { langCode: [speaker, ...] } }. No API key required. Optionally filter by `model` (e.g. 'coda', 'mistv3', 'arcana') and/or `language` (the ISO 639-2 catalog key, e.g. 'eng'), and cap output with `limit` (max speakers per model+language list). Use get_voice_details for demographics and the exact `lang` value to pass to synthesize_speech.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","properties":{"limit":{"type":"integer","exclusiveMinimum":0},"model":{"type":"string"},"language":{"type":"string"}},"additionalProperties":false},"title":"List Rime voices","annotations":{"readOnlyHint":true,"untrustedContentHint":true},"logicalName":"list_voices","displayName":"List Rime voices"},{"name":"get_voice_details","description":"Return detailed metadata for Rime voices (gender, age, accent/dialect, country, genre, model, and language). This is where the `lang` value for synthesize_speech comes from, and it carries the demographic metadata you use to choose a voice. No API key required. All filters are optional and applied client-side: `speaker`, `model`, `gender`, `language` (matches either the `language` or `lang` field).","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","properties":{"model":{"type":"string"},"gender":{"type":"string"},"speaker":{"type":"string"},"language":{"type":"string"}},"additionalProperties":false},"title":"Get Rime voice details","annotations":{"readOnlyHint":true,"untrustedContentHint":true},"logicalName":"get_voice_details","displayName":"Get Rime voice details"},{"name":"check_dictionary","description":"Check which words are NOT in Rime's pronunciation dictionary. Returns the list of out-of-dictionary words; an empty list means all words are covered. Out-of-dictionary words still synthesize, but you may want to add custom pronunciations for them. Requires RIME_API_KEY.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["text"],"properties":{"text":{"type":"string","minLength":1}},"additionalProperties":false},"title":"Check Rime dictionary coverage","annotations":{"readOnlyHint":true,"untrustedContentHint":true},"logicalName":"check_dictionary","displayName":"Check Rime dictionary coverage"},{"name":"normalize_text","description":"Preview how Rime normalizes text before synthesis — exactly what the TTS model will speak. Useful for debugging numbers, dates, phone numbers, currency, and abbreviations. Returns the normalized string. Requires RIME_API_KEY.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["text"],"properties":{"text":{"type":"string","minLength":1}},"additionalProperties":false},"title":"Preview Rime text normalization","annotations":{"readOnlyHint":true,"untrustedContentHint":true},"logicalName":"normalize_text","displayName":"Preview Rime text normalization"},{"name":"synthesize_speech","description":"Generate an MP3 speech sample from text using Rime TTS, rendered in an inline audio player. All arguments are optional: with none, it plays a default sample in the canonical demo voice (`lyra` on the `coda` flagship model) — the fastest way to hear Rime. Choose `speaker` and `modelId` from list_voices / get_voice_details to try others. The `language` argument is optional: by default it is omitted and Rime infers the language from the speaker (works for English); when provided it is sent as `lang","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","properties":{"text":{"type":"string","default":"Hi, I'm a Rime voice. This is what I sound like.","maxLength":2000,"minLength":1},"modelId":{"type":"string","default":"coda"},"speaker":{"type":"string","default":"lyra"},"language":{"type":"string"},"include_audio":{"type":"boolean","default":false}},"additionalProperties":false},"title":"Synthesize speech with Rime","logicalName":"synthesize_speech","displayName":"Synthesize speech with Rime","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"generate_integration","description":"Generate a ready-to-run code snippet for wiring Rime TTS into a voice agent framework (Pipecat or LiveKit). Returns install commands, code, and .env notes. No network call. Pipecat is Python-only. For LiveKit, `mode` selects 'plugin' (use your own Rime key) or 'inference' (run on LiveKit Cloud, no Rime key).","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["framework"],"properties":{"mode":{"enum":["plugin","inference"],"type":"string","default":"plugin"},"model":{"type":"string","default":"coda"},"speaker":{"type":"string","default":"lyra"},"language":{"enum":["python","node"],"type":"string","default":"python"},"framework":{"enum":["pipecat","livekit"],"type":"string"}},"additionalProperties":false},"title":"Generate a Rime integration snippet","annotations":{"readOnlyHint":true,"untrustedContentHint":true},"logicalName":"generate_integration","displayName":"Generate a Rime integration snippet"}],"toolSource":"directory_preview","agentAction":"both","installLinks":[{"id":"cursor","label":"Cursor","href":"cursor://anysphere.cursor-deeplink/mcp/install?name=Rime-Conversational-Voice-AI&config=eyJ1cmwiOiAiaHR0cHM6Ly9tY3AucmltZS5haS9tY3AifQ%3D%3D"},{"id":"vscode","label":"VS Code","href":"vscode:mcp/install?%7B%22name%22%3A%22Rime-Conversational-Voice-AI%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.rime.ai%2Fmcp%22%7D"},{"id":"vscode-insiders","label":"VS Code Insiders","href":"vscode-insiders:mcp/install?%7B%22name%22%3A%22Rime-Conversational-Voice-AI%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.rime.ai%2Fmcp%22%7D"},{"id":"claude-web","label":"Claude.ai","href":"https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Rime+%7C+Conversational+Voice+AI&connectorUrl=https%3A%2F%2Fmcp.rime.ai%2Fmcp"},{"id":"codex","label":"Codex","copyText":"codex mcp add \"Rime-Conversational-Voice-AI\" --url \"https://mcp.rime.ai/mcp\""},{"id":"chatgpt","label":"ChatGPT","href":"https://www.mcpbundles.com/docs/integrations/chatgpt"}],"catalogUrl":"https://www.mcpbundles.com/api/directory/v1/servers/rime-mcp-64636189bd","callUrl":"https://www.mcpbundles.com/api/directory/v1/servers/rime-mcp-64636189bd/tools/{tool}","mcpServerUrl":"https://mcp.rime.ai/mcp","liveCatalogUrl":"https://www.mcpbundles.com/api/directory/v1/servers/rime-mcp-64636189bd?live=1"}