Inworld AI for AI agents

Inworld AI provides speech synthesis, speech recognition, and voice management for building conversational voice experiences. Teams building AI products use it to add this capability without training or hosting their own model. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect Inworld AI See the 6 actions ↓

AI and modelsAPI keyMCP + RESTinworld.ai

AUDIT LOG · INWORLD AIPOLICY: acme-support

09:41:07 · claude · u_8f2read

inworld_ai.list_models

List Models✓ allowed · 212ms

09:41:08 · claude · u_8f2read

inworld_ai.list_voices

List Voices✓ allowed · 164ms

09:41:09 · claude · u_8f2write

inworld_ai.create_embeddings

Create Embeddings✓ approved · approved by user

EVERY INWORLD AI CALL, ON THE RECORD

01 · USE CASES

What agents do in Inworld AI.

Synthesize speech from text

Convert a script into spoken audio using a chosen voice for a character or narration.

Transcribe an audio clip

Transcribe a recorded audio clip into text for review or captioning.

List available voices

List available voices to pick the right one for a new interactive character.

02 · ACTIONS

6 Inworld AI actions, graded by risk.

Every Inworld AI action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

Look things up. Allowed by default.

inworld_ai.list_models
List Models
inworld_ai.list_voices
List Voices
inworld_ai.get_voice_preview
Get Voice Preview

write

Create and change things. Allow, or ask the user first.

inworld_ai.create_embeddings
Create Embeddings
inworld_ai.transcribe_audio
Transcribe Audio
inworld_ai.synthesize_speech
Synthesize Speech

destructive

Delete, cancel or archive. Ask first, or deny outright.

No destructive actions.

03 · HOW IT WORKS

Inworld AI in three steps.

01Your users connect Inworld AIThey add their Inworld AI api key on Arc0 Connect, under your brand. It goes straight into the vault.
02You set the rulesReads run, and writes like “create Embeddings” can wait for the user to approve.
03Any agent can actYour agent calls Inworld AI through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.

POLICY.TS

await arc0.policies.set('inworld_ai', {
  read: 'allow',
  write: 'ask',        // create_embeddings
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2

04 · AUTH AND DATA

How Inworld AI connects.

Users add their Inworld AI api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Inworld AI connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH: API key
CREDENTIALS: Per-tenant encrypted vault
MODEL SEES: Results only, never credentials
AUDIT LOG: Every call, on every plan

05 · WORKS WITH

Use Inworld AI from any agent.

Claude

ChatGPT

Cursor

Codex

VS Code

OpenAI Agents SDK

Claude Agent SDK

Vercel AI SDK

Mastra

LangGraph

06 · RELATED

More ai and models apps.

Perplexity AI9 actions

All Images AI7 actions

AltText.ai10 actions

AltTextLab2 actions

ALL AI AND MODELS APPS →

07 · FAQ

Inworld AI and Arc0, answered.

Q01

Can I use Inworld AI with Claude, ChatGPT or Cursor?

Yes. Connect Inworld AI to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Inworld AI actions you allow.

Q02

How do users connect Inworld AI?

Users add their Inworld AI api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Inworld AI actions can my agent take?

6 in total: 3 read, 3 write and 0 destructive, such as “create Embeddings”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Inworld AI?

Yes. Allow read actions and deny writes in the Inworld AI policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Inworld AI too?

Yes. The same Inworld AI connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Inworld AI into your agent.

Your users connect Inworld AI once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.

Connect Inworld AI Browse all apps →

Free to build · MCP + REST · Audit log on every plan