# Gradium — MCP server on mcp.ai
> Connect your Gradium account and use 9 tools for artificial intelligence straight from your AI agent. Connect with your own API key. Gradium provides low-latency speech generation, transcription, voice management, and pronunciation tools for real-time voice applications.

By: mcp.ai · official
Page: https://mcp.ai/gradium

## Connect (MCP protocol)
Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_gradium?ms=1787291520000
Add it as a custom/remote MCP connector, then authenticate when prompted.

## REST API (no MCP client required)
Every tool is also a REST endpoint, authed with a workspace API key.
Discover: GET https://api.mcp.ai/api/gradium/_endpoints   # public; lists every endpoint
Call:     POST https://api.mcp.ai/api/gradium/<endpoint>
  Authorization: Bearer sk_live_…   # create one at https://mcp.ai/settings/api-keys
  Content-Type: application/json
  Body: { …args }   →   { "ok": true, "tool": "<id>", "result": { … } }

## Developer docs
How to use (MCP or REST), markdown: https://mcp.ai/gradium/skill.md
Postman collection (v2.1): https://mcp.ai/gradium/postman.json

## Tools
- gradium_create_pronunciation_dictionary(name: string, rules?: object[], language: string, description?: string) — Create a language-specific pronunciation dictionary with optional rewrite rules.
- gradium_delete_pronunciation_dictionary(uid: string) — Permanently delete one pronunciation dictionary by UID.
- gradium_get_credits() — Get the connected Gradium subscription's current credit balance and billing-period metadata.
- gradium_get_pronunciation_dictionary(uid: string) — Retrieve one pronunciation dictionary and its complete rewrite rule set by UID.
- gradium_get_usage_summary() — Retrieve aggregate Gradium session, message, text, audio-duration, and consumed-credit usage totals.
- gradium_get_voice(voice_uid: string) — Retrieve metadata for one Gradium catalog or custom voice by its UID.
- gradium_list_pronunciation_dictionaries(language?: string, page_size?: integer, next_cursor?: string) — List pronunciation dictionaries for the connected organization, optionally filtered by language.
- gradium_list_voices(page_size?: integer, next_cursor?: string, include_catalog?: boolean) — List custom voices and, by default, Gradium's public voice catalog, returning voice IDs and metadata for later selection.
- gradium_update_pronunciation_dictionary(uid: string, name?: string, rules?: object[], language?: string, description?: string) — Update pronunciation dictionary metadata and optionally replace its complete rewrite rule set.

## Example prompts
- "What can I do in Gradium?"
- "Show me a summary of my Gradium account"

## Links
Docs: https://mcp.ai/docs/mcps/gradium
Website: https://mcp.ai/mcps/gradium