# Inworld AI — MCP server on mcp.ai
> Connect your Inworld AI account and use 6 tools for artificial intelligence straight from your AI agent. Connect with your own API key. Inworld AI provides native APIs for speech synthesis, speech recognition, voice management, model discovery, embeddings, knowledge, and router management.

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

## Connect (MCP protocol)
Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_inworld_ai?ms=1787291400000
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/inworld_ai/_endpoints   # public; lists every endpoint
Call:     POST https://api.mcp.ai/api/inworld_ai/<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/inworld_ai/skill.md
Postman collection (v2.1): https://mcp.ai/inworld_ai/postman.json

## Tools
- inworld_ai_create_embeddings(texts: string[], model_id?: string, service_provider?: string) — Generate one complete embedding vector per input text with an Inworld-hosted embedding model. Batches can produce large responses.
- inworld_ai_get_voice_preview(model_id: string, voice_id: string) — Generate the provider-selected, unmetered MP3 preview for a voice and return it as a downloadable file.
- inworld_ai_list_models() — List Inworld-supported models and the pricing, modality, context, and output limits needed to choose a model. The endpoint returns the complete model catalog and can produce a moderately large respons
- inworld_ai_list_voices(cursor?: string, filter?: string, order_by?: string, languages?: string[], page_size?: integer) — Return one page of voices available for preview or speech synthesis, with optional filtering, language selection, and sorting. The filter and languages parameters are mutually exclusive.
- inworld_ai_synthesize_speech(text: string, bit_rate?: integer, language?: string, model_id: string, voice_id: string, speaking_rate?: number, audio_encoding?: string, sample_rate_hertz?: integer, enhance_generation?: boolean, apply_text_normalization?: string) — Synthesize short text with an Inworld voice and return the complete audio as a downloadable file. Long text can exceed tool payload limits; prefer short text and compressed MP3 output.
- inworld_ai_transcribe_audio(prompts?: string[], language?: string, model_id?: string, audio_file: object, audio_encoding?: string, sample_rate_hertz?: integer, number_of_channels?: integer, include_word_timestamps?: boolean) — Synchronously transcribe a short audio file and return the final transcript, timestamps, and usage. Prefer compressed input to limit base64 payload growth.

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

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