Home / Servers / ElevenLabs API / create_speech_engine

Create Speech Engine

An MCP tool from the ElevenLabs API server, hosted on mcp.hjlabs.in.

Create Speech Engine Create a new Speech Engine resource [POST /v1/speech-engine]

Name on the gateway: elevenlabs_api__create_speech_engine · may change things.

Parameters

Name	Type	Description
`name`	`string`	Name of the speech engine
`speech_engine` required	`object`	Speech engine WebSocket configuration
`asr`	`object`	ASR configuration
`tts`	`object`	TTS configuration
`turn`	`object`	Turn detection configuration
`vad`	`object`	Configuration for voice activity detection
`conversation`	`object`	Conversation configuration (client events, etc.)
`privacy`	`object`	Privacy settings (recording, retention, zero retention mode)
`call_limits`	`object`	Concurrency and daily conversation limits for this speech engine
`auth`	`object`	Who may start a conversation with this speech engine
`language`	`string`	Language for the speech engine
`cascade_timeout_seconds`	`number`	Time in seconds to wait for the upstream speech engine endpoint to respond…
`tags`	`array`	Tags for categorization
`overrides`	`object`	Override settings the client may set during conversation initiation

Through the Smart Gateway, any client can run it by name with call_tool, or let the gateway find it with search_tools:

call_tool arguments

{
  "name": "elevenlabs_api__create_speech_engine",
  "arguments": {
    "speech_engine": "…"
  }
}

Or connect the ElevenLabs API server directly, which lists 487 tools including this one:

Run in your terminal

claude mcp add --transport http hj-elevenlabs-api https://mcp.hjlabs.in/mcp/elevenlabs-api \
  --header "Authorization: Bearer YOUR_API_KEY"

Use the create speech engine tool with name set to ….