
by Inworld
Inworld provides realtime text-to-speech, speech-to-text, speech-to-speech and LLM inference APIs aimed at consumer apps such as companions, tutors and games.
APIUsage-based
Step 1: Open the Inworld site and get an API key.
Step 2: Try the voices and models in the playground.
Step 3: Read the quickstart for the product you need, such as text to speech or the realtime API, in the docs.
Step 4: Call the API from your app, or install the CLI with npm to use it from a terminal.
Step 5: Choose a plan on the pricing page when you move to production.
Yes. The realtime API listens, reasons and talks back on one WebSocket or WebRTC connection, and you can use any LLM per session.
Voice is available in the US, Europe, India and Asia Pacific, while LLM serving is in the US. Inworld lists SOC 2 Type II, HIPAA and GDPR, and Enterprise adds EU and India data residency.
The pages say the realtime text-to-speech model covers about 500 languages and dialects.
The docs offer a docs MCP server and a copyable skill for coding agents such as Claude Code and Cursor, so the assistant can use the Inworld docs.
ConvaiConvai is a platform for building conversational 3D AI characters that can see, hear and act in games, XR and virtual worlds, with plugins for Unity and Unreal Engine.
Rosebud AIRosebud AI is a browser-based platform where you describe a game and an AI assistant builds a playable 2D or 3D version. Games publish as a link that plays in any browser.