Skip to main content
The Inworld CLI is the fastest way to use Inworld from your terminal — authenticate, create API keys, synthesize speech, transcribe audio, chat through the LLM Router, and run the Inworld MCP server. It’s a single global package with no project setup or SDK installation required. It’s also built for AI coding agents: an agent can log in, mint an API key, and call Inworld APIs directly from the shell — no MCP server configuration needed. 
npm install -g @inworld/cli
Requires Node.js 20+. The package installs two commands: inworld (the CLI) and inworld-mcp (the standalone MCP server, equivalent to inworld mcp).

​
Authentication

# Authenticate with Inworld Platform (opens browser)
inworld login

# Check current authentication status and configuration
inworld status
Credentials are stored securely on your machine (macOS Keychain, Windows Credential Manager, or an encrypted file on Linux) and refreshed automatically. For CI or other non-interactive environments, either authenticate with a Firebase ID token or set an API key directly: 
# Exchange a Firebase ID token (e.g., from your CI's OIDC flow)
inworld auth login-ci --token "$FIREBASE_ID_TOKEN"

# Or skip login entirely with an API key
export INWORLD_API_KEY="..."

​
Workspaces and API keys

# Select a workspace for CLI operations
inworld workspace select

# Create a new API key (read-only by default)
inworld workspace add-key --name my-key

# Create a key with read/write permissions for voices and router
inworld workspace add-key --write --name my-key

# Make a key the active one for CLI commands (new keys are not auto-selected)
inworld workspace select-key

# Print the current API key (e.g., to export it as an environment variable)
inworld auth print-api-key

​
Text-to-Speech

# List available voices
inworld tts list-voices

# Synthesize text to speech
inworld tts synthesize "Hello world" --voice Dennis --output hello.mp3

# Synthesize and play through speakers
inworld tts synthesize "[happy] Great to see you!" --play

# Clone a voice from an audio file (5-15 seconds, max 4MB)
inworld tts clone sample.wav --name "My Voice"

# Design a voice from a text description (interactive wizard)
inworld tts design "A warm, deep narrator voice with a slight British accent"
synthesize supports audio markups directly in the text: emotions ([happy], [sad]), delivery styles ([whispering]), vocalizations ([laugh], [sigh]), SSML breaks, and IPA pronunciation.

​
Speech-to-Text

# Transcribe an audio file
inworld stt transcribe recording.wav

# Transcribe with a specific language
inworld stt transcribe recording.mp3 --lang es-ES

​
LLM Router

# List models available to your workspace
inworld llm models

# Send a chat completion request
inworld llm chat "What is the capital of France?" --model gpt-4o-mini

​
MCP server

The CLI ships with the full Inworld MCP server — your AI assistant gets real operational tools, not just documentation search: TTS previews, voice design and publishing, STT transcription, LLM chat, workspace search and limits, billing summary, and router + BYOK credential management. 
# Run as a stdio MCP server (for Claude Code, Cursor, etc.)
inworld mcp        # or the standalone bin: inworld-mcp

# Or run over HTTP
inworld mcp --http --port 3333
For example, to add it to Claude Code: 
claude mcp add inworld -- inworld mcp
Many agents don’t need the MCP server at all — they can call inworld commands directly from the shell.

​
Telemetry

The CLI collects anonymous usage analytics. To opt out: 
inworld auth disable_cli_telemetry

​
Inworld CLI vs. Runtime CLI

The Inworld CLI (inworld) covers platform APIs: auth, API keys, TTS, STT, and LLM Router. For Agent Runtime graph development and deployment (inworld-runtime init/run/deploy), see the Runtime CLI.