At a glance
It's time to bring your most ambitious AI applications to life with emotionally intelligent, real-time voice AI from Inworld. You can use Inworld's pre-built voices or clone your own from a few seconds of audio in Inworld's API and via LiveKit's Agents framework. Inworld's multi-lingual, expressive voices are state-of-the-art quality with real-time latency, at a price up to 16x lower than alternative providers. You can learn more about Inworld's text-to-speech (TTS) models on the Inworld text-to-speech page.
Inworld voices and text-to-speech models can be accessed through LiveKit's agents framework plugin. Developers can create real-time voice experiences such as multiplayer games, agentic NPCs, customer-facing avatars, live training simulations, and more at an accessible price.
Experience Realtime TTS in a voice-driven, tabletop RPG game built by the LiveKit team. You can access the GitHub code repository to build your own voice-first, multi-agent game experience.
“Our TTS modeling framework allows us to advance voice AI's emotional and contextual understanding and easily add new functionality, while keeping costs affordable. This helps democratize access to building high-quality, real-time voice experiences.”
Jean Wang, Head of Product, Inworld
Use case 01
Natural, conversational speech
Combine LiveKit's programmable audio pipeline with Inworld's state-of-the-art TTS and natural-language steering for emotionally grounded, turn-based dialogue and instant feedback. Realtime TTS-2 takes direction in plain words in the request's instruction field, and Speech Reasoning, in beta, reads the conversation and writes that direction for you. Control voice switching and audio routing dynamically.
Use case 02
Accessible pricing
Studio-quality voices priced per character, and the rate falls as you grow: Realtime TTS-2 starts at $25 per 1M characters and goes as low as $5 at Enterprise scale. At that rate it's up to 16x lower than alternative providers, so you can build engaging experiences that scale with your users.
Use case 03
Real-time latency
Generate and stream Inworld voices with first audio in as little as 50 ms via LiveKit's global edge infrastructure, which is ideal for real-time experiences with proven reliability in high-concurrency environments.
Use case 04
Zero-shot voice cloning
Leverage Inworld's voice cloning capabilities to bring characters, brands, user-generated content, and more to life with emotion and personality using just 3 to 30 seconds of audio.
Use case 05
Multilingual voices
Build agents in about 500 languages and dialects on Realtime TTS-2, including English (with its various accents), Chinese, Korean, Dutch, French, Spanish, and more. You can also preserve accents for a specific voice when switching languages.
Use case 06
Designed for developers
Build consumer applications with LiveKit's SDKs for web, mobile, and Unity. Craft custom voice pipelines using third-party integrations, RAG, and function calling. LiveKit's Agent framework also comes with performance metrics and debugging tools.
“Latency has a direct impact on user experience, and developers must consider how to manage it effectively. Fast models help, but efficient data streaming, optimized network communication, and prompting can also be crucial. Metrics like 'first response latency' are key. Developers should consider this not only in the models they use, but also in how they implement their applications.”
Michael Solati, Developer Advocate, LiveKit
What’s next
Built for builders
Get started in just minutes. Use LiveKit's Agent framework to stream audio via Inworld's TTS endpoint with the LLM and STT providers of your choice. Configure voice parameters, natural-language steering, and even language switching using Inworld's API. Then deploy your agent to LiveKit's global infrastructure, allowing you to speak to your agent with real-time latency from anywhere in the world.
Ready to start building? Explore the LiveKit text-to-speech documentation, the Inworld text-to-speech overview, and the Inworld text-to-speech documentation.
Let's talk
Inworld x LiveKit collaboration
Whether you are building immersive games, voice-first apps or agentic tools, Inworld + LiveKit is designed to give you full-stack control with real-world performance.
Inworld and LiveKit hosted a Realtime AI Meetup in San Francisco, where hundreds of voice AI developers, founders, and enthusiasts gathered to explore how text-to-speech and speech-to-text models are built, key considerations for development, and how to maximize their potential in AI agents.
