Build scalable AI experiences and characters for games and media with Inworld Runtime. The AI infrastructure trusted by Xbox, Ubisoft, & NVIDIA.

The new AI infrastructure for scaling games, media, and characters

<article>
  <h3>Built on gaming and media innovation</h3>
  <p>
    We began by pushing the frontier of lifelike, interactive <span class='font-bold'>characters</span> for
    games and entertainment, and this remains a core focus area. Today, Inworld
    powers real‑time, voice‑forward experiences and provides the infrastructure
    that lets those experiences scale from a prototype to millions of players
    without sacrificing quality. Partners across the industry, including <a href='https://inworld.ai/blog/xbox-partners-with-inworld-ai-to-build-generative-ai-tools-for-game-development' rel='noopener noreferrer' target='_blank'>Xbox</a>,
    <a href='https://inworld.ai/blog/nvidia-inworld-ai-demo-on-device-capabilities' target="_blank" rel="noopener noreferrer">NVIDIA</a>, <a href='https://inworld.ai/blog/ubisoft-neo-npc-prototype' rel='noopener noreferrer' target='_blank'>Ubisoft</a>, <a href='https://inworld.ai/blog/interactive-learning-with-niantic-inworld' rel="noopener noreferrer" target='_blank'>Niantic</a>, <a target="_blank" rel="noopener noreferrer" href='https://lift.comcast.com/2023/08/14/inworlds-ai-revolution-breathing-life-into-virtual-characters-for-gaming-and-beyond/'>NBCUniversal</a>, <a href='https://inworld.ai/blog/streamlabs-unveils-intelligent-streaming-assistant-built-in-collaboration-with-inworld-and-nvidia'>Streamlabs</a>, <a href='https://inworld.ai/blog/unity-inworld-ai-marketplace' rel='noopener noreferrer' target='_blank'>Unity</a> and <a href='https://inworld.ai/blog/inworld-awarded-epic-megagrant' rel='noopener noreferrer' target='_blank' >Epic</a>, have
    built with Inworld to explore new gameplay and audience experiences.
  </p>

  <p>
    Long before “chat with anything” became a category, we were shipping
    playable, <span class='font-bold'>character‑centric</span> demos and engine integrations that let teams
    imagine worlds where characters remember, react, and stay in‑world. That
    early craft in character design is still our foundation, and it is why
    leading studios and platforms continue to collaborate with us on the next
    generation of character‑driven interactive media.
  </p>
  <h3>
    From demos to production: Deeper control through a new AI infrastructure
  </h3>
  <p>
    As partners moved from impressive demos to live titles, we hit the same wall
    every game team hits: keeping <span class='font-bold'>voice, timing, and consistency flawless at
    scale</span>, which is what players actually feel. Text‑only stacks and one‑off
    integrations were not built for <span class='font-bold'>real‑time, multimodal</span> workloads, and
    stitching providers together left developers without enough <span class='font-bold'>control</span> to
    maintain user‑facing quality as usage spiked or audiences expanded.
  </p>

  <p>
    That is why we built <a href='https://inworld.ai/runtime'>Runtime</a>: to put developers in control of <span class='font-bold'>the entire pipeline</span>, and to make <span class='font-bold'>measurement and experimentation</span> first‑class</span>, so
    pipeline, and to make measurement and experimentation first‑class, so
    quality can be maintained and extended to new geographies and demographics,
    with personalization where it matters.
  </p>

  <h3>What is Inworld Runtime and how does it help you scale?</h3>

  <p>
    <a href='https://inworld.ai/runtime'>Inworld Runtime</a> is a high‑performance, C++ graph engine (with SDKs like
    Node.js and Unreal) that orchestrates LLMs, STT, TTS, memory or knowledge,
    and tools in a single pipeline. Build a graph in code, ship it, then iterate
    with remote configuration, A/B variants (via Graph Registry), and built‑in
    telemetry without redeploying your game. It is the infrastructure we
    developed to support experiences with millions of concurrent users, now
    available to all developers.
  </p>

  <p>Why this gives you more control and keeps quality tangible for users</p>
  <ul>
    <li>
      Provider‑agnostic nodes so you can swap models and services without
      glue‑code churn or lock‑in.
    </li>
    <li>
      Remote config and Graph Registry to change prompts, models, and routing
      live, safely rolled out to cohorts.
    </li>
    <li>
      Targeted experiments to validate interaction quality for new geographies
      and demographics, including voices, timing, interruptions, prompts, and
      routing, and enabling personalization by segment.
    </li>
    <li>
      Observability for player‑perceived quality with traces, dashboards, and
      logs that expose latency paths, first‑audio timing, and lip‑sync cadence
      so you fix what users actually feel.
    </li>
  </ul>
  <p>
    The approach is simple: one runtime for your entire multimodal pipeline
    (e.g. STT → LLM → TTS → game or media state), with observability and
    experimentation to optimize quality, latency, and cost for every audience.
  </p>
  <h3>Voice that keeps up with gameplay</h3>
  <p>
    Many teams start with TTS, then expand into full pipelines as they localize,
    personalize, and harden for live ops, testing variations for new geographies
    and demographics and locking in what works.
  </p>
  <p>
    <a href='https://docs.inworld.ai/docs/tts/tts'>Inworld TTS</a> delivers expressive, natural‑sounding speech built for real‑time
    play. You get low‑latency streaming, instant voice cloning, and timestamp
    alignment for lip‑sync and captions, plus multi‑language coverage and
    <a href='https://docs.inworld.ai/docs/tts/integrations'>integrations</a> with LiveKit, NLX, Pipecat, and Vapi for end‑to‑end real‑time
    agents. Pricing starts at $5 per 1M characters, so you can scale voice
    across large audiences. <a href='https://docs.inworld.ai/docs/tts/tts-playground'>Try the TTS Playground</a> or call the API to <a href='https://docs.inworld.ai/docs/tts/integrations'>integrate</a>
    quickly.
  </p>

  <h3>Proven at scale with industry leaders in games and media</h3>
  <ul>
    <li>
      <a href='https://inworld.ai/blog/xbox-partners-with-inworld-ai-to-build-generative-ai-tools-for-game-development' target="_blank" rel="noopener noreferrer">Xbox × Inworld</a>: Multi‑year co‑development to enrich narrative and
      character creation for game developers.
    </li>
    <li>
      <a href='https://inworld.ai/blog/ubisoft-neo-npc-prototype' rel='noopener noreferrer' target='_blank'>Ubisoft (NEO)</a>: Prototype showcased real‑time reasoning, perception, and
      awareness in characters powered by Inworld tech.
    </li>
    <li>
      <a href='https://inworld.ai/blog/gdc-2024' target="_blank" rel="noopener noreferrer">NVIDIA (Covert Protocol)</a>: Social simulation and hybrid on‑device or cloud
      capabilities using NVIDIA ACE with Inworld.
    </li>
    <li>
      <a href='https://inworld.ai/blog/interactive-learning-with-niantic-inworld' rel="noopener noreferrer" target='_blank'>Niantic</a>: From Wol to WebAR, teams used Inworld to bring AI characters into
      spatial experiences.
    </li>
    <li>
      <a href='https://inworld.ai/blog/streamlabs-unveils-intelligent-streaming-assistant-built-in-collaboration-with-inworld-and-nvidia' target="_blank" rel="noopener noreferrer">Streamlabs</a>: Intelligent streaming assistant jointly powered by Streamlabs,
      NVIDIA ACE, and Inworld generative AI.
    </li>
    <li>
      NBCUniversal and other media leaders: <a href='https://docs.inworld.ai/docs/runtime/overview' target="_blank" rel="noopener noreferrer">Runtime</a> opened after building
      infrastructure to meet their scale and quality bars.
    </li>
  </ul>
  <h3>Continuing our character leadership at scale</h3>
  <p>
    We pioneered character‑first, real‑time interaction years before today’s
    wave. That DNA is alive and well, and now it is backed by an infrastructure
    layer that gives developers more control and a better fit for modern
    production: Runtime for orchestration and TTS for voice that performs under
    pressure. If you knew us for our previous character stack, you will find
    this generation faster to ship, safer to iterate, and easier to scale.
  </p>
  <p>Learn more about how to <a href='https://docs.inworld.ai/docs/guides/runtime-character' target="_blank">create characters with Runtime</a></p>
  <h3>How do I get started with Inworld Runtime?</h3>
  <ul>
    <li>Explore the <a href='https://docs.inworld.ai/docs/runtime/overview' target="_blank" rel="noopener noreferrer">Runtime Overview</a>  for graphs, experimentation, and observability</li>
      <li><a href='https://docs.inworld.ai/docs/templates'>Try our Templates</a> for Node.js CLI, Voice Agent, Language Learning, and Companion apps</li>
      <li>Test TTS capabilities in our <a href='https://docs.inworld.ai/docs/tts/tts-playground' rel="noopener noreferrer" target='_blank'>TTS Playground</a></li>
      <li>Check <a href='https://docs.inworld.ai/docs/tts/integrations' target="_blank" rel="noopener noreferrer">integrations</a> with LiveKit, Pipecat, Vapi, and NLX</li>
      <li><a href="https://inworld.ai/contact-sales">Contact our team</a> if you're scaling voice-first or character-driven experiences</li>
    </li>
  </ul>

  <p>Unreal (Runtime) is available now for early access. Unity is coming soon. If you are scaling a voice‑first or character‑driven experience in games or media, we would love to help you map the pipeline and quality targets that matter for your audience. Start with the Runtime Overview and Templates.</p>
<h3>Powering the future of interactive media</h3>
<p>We are uniting believable AI characters and worlds with the runtime required to run them at multi‑million‑user scale. Build the worlds you want, with characters that truly come alive and stay alive, at scale.</p>
</article>

<style>
  .blog-post-hero p {
    color: #212120 !important;
  }

  .simple-page-slice div:has(> img.object-cover) {
    display: none !important;
  }

  article .quote {
    position: relative;
  }
  article .attribution__name,
  article .attribution__title {
    font-weight: 600;
    font-family: var(--font-sans);
    font-size: 1rem;
  }

  article .quote::before {
    content: "“";
    font-size: 1rem;
    position: absolute;
    top: 0;
    left: -0.5rem;
    font-weight: 400;
    color: #212120;
  }
  article .attribution {
    font-size: 1rem;
  }
  article a {
    text-decoration: underline;
    font-size: 1rem;
    font-family: var(--font-serif);
  }

  article ul {
    list-style-type: disc;
    padding-left: 1rem;
  }

  article p,
  article li {
    font-family: var(--font-serif);
    line-height: 1.6;
    font-size: 1rem;
    color: #212120;
    margin-bottom: 1rem;
  }
  article h3 {
    font-size: 1.5rem;
    margin-top: 3rem;
    font-family: var(--font-serif-display);
    color: #212120;
    margin-bottom: 1rem;
  }
</style>
