Inworld Runtime
Powering the best realtime AI apps with LLMs and voice models.
Model-agnostic realtime orchestration. Integrated observability. Easy experiments to learn which models optimize user metrics.
Model-agnostic realtime orchestration. Integrated observability. Easy experiments to learn which models optimize user metrics.
Build Interactive AI Applications
The best LLMs, voice models and orchestration for interactive apps.
Why Inworld Runtime
Inworld Runtime gives you the best quality, availability and speed
Exceptional Quality
Serve personalized models and prompts to delight every user.
High Availability
Automatic failovers prevent downtime from outages and rate limits.
Ultra Low Latency
Lightning-fast execution that scales seamlessly from 10 to 10M users with minimum code changes.
Proven Results
Built for every consumer AI application - from social apps and games to learning and wellness.
Bible Chat
Increased voice AI feature engagement and reached millions
Built for every consumer AI application
Runtime scales consumer AI, driving experiences from social apps and games to learning and wellness.
Get started
Inworld easily integrates with any existing stack or provider (Anthropic, Google, Mistral, OpenAI, etc.) via one API key.
Available to everyone now.
FAQ
How is Runtime different from other AI backends?
The Inworld Runtime uniquely combines
- lightning-fast C++ core for realtime multimodal conversational interactions.
- built-in telemetry for deep user insights (traces & logs).
- live A/B testing to accelerate improvements to the end user experience.
Is Runtime free?
Yes, Runtime is free. Consumption of models is the only thing you pay for. Runtime itself incurs no cost or license fee. Learn more about model pricing here.
How do I get started?
Follow our quick start guide to deploy a realtime conversational AI endpoint in 3 minutes - Then integrate into your app.
Who is Inworld Runtime designed for?
Inworld Runtime is specifically designed for developers building realtime conversational AI and voice agents that scale to millions of concurrent users.
Use cases include language tutors, social media, AI companions, game characters, fitness coaches, social media, shopping agents, and more.
Can Inworld Runtime work with my existing framework and stack?
Yes, you can use the Inworld CLI to deploy a hosted endpoint that can be easily called by any part of your existing stack.
What production-ready building blocks does Inworld Runtime provide?
Developers get a full suite of pre-optimized nodes to construct any real-time AI pipeline that can scale to millions of users, including nodes for
- model I/O (STT, LLM, TTS)
- data engineering (prompt building, chunking)
- flow logic (keyword matching, safety)
- external tool calls (MCP integrations)
- and more
What LLM, TTS, STT, and embedding models do you support?
What is an example runtime LLM -> TTS pipeline?
const graphBuilder = new SequentialGraphBuilder({
id: 'llm-tts-graph',
nodes: [
new RemoteLLMChatNode({
provider: 'openai',
modelName: 'gpt-4o-mini',
stream: true,
messageTemplates: [
{
role: 'user',
content: {
type: 'template',
template: '{{user_input}}',
},
},
],
}),
new TextChunkingNode(),
new RemoteTTSNode({
speakerId: 'Ashley',
modelId: 'inworld-tts-1',
sampleRate: 24000,
}),
],
enableRemoteConfig: false
});