# Inworld AI — how to use (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.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_inworld_ai?ms=1787293500000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `inworld_ai_create_embeddings`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/inworld_ai`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/inworld_ai/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/inworld_ai/create/embeddings` — Generate one complete embedding vector per input text with an Inworld-hosted embedding model. Batches can produce large responses.
  - body: { texts: string[], model_id?: string, service_provider?: string }
- `POST https://api.mcp.ai/api/inworld_ai/get/voice/preview` — Generate the provider-selected, unmetered MP3 preview for a voice and return it as a downloadable file.
  - body: { model_id: string, voice_id: string }
- `POST https://api.mcp.ai/api/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
- `POST https://api.mcp.ai/api/inworld_ai/list/voices` — 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.
  - body: { cursor?: string, filter?: string, order_by?: string, languages?: string[], page_size?: integer }
- `POST https://api.mcp.ai/api/inworld_ai/synthesize/speech` — 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.
  - body: { 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 }
- `POST https://api.mcp.ai/api/inworld_ai/transcribe/audio` — Synchronously transcribe a short audio file and return the final transcript, timestamps, and usage. Prefer compressed input to limit base64 payload growth.
  - body: { 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 }

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

## More
- Page: https://mcp.ai/inworld_ai
- Agent spec (llms.txt): https://mcp.ai/inworld_ai/llms.txt
- Postman collection: https://mcp.ai/inworld_ai/postman.json