Now you can build interactive voice applications that integrate seamlessly with digital channels, using Inworld’s state-of-the-art voice AI. Inworld’s text-to-speech (TTS) delivers studio quality and real-time latency, but at ~5% of the cost of alternatives. You can learn more about Inworld’s TTS models here.
Why Inworld + NLX for Voice+ AI
Consumers want to be able to interact with voice experiences in a way that feels authentic - whether that means through more expressive conversations or different modes of engagement. You can now access Inworld’s pre-built voices or clone your own voice to build interactive, voice-first applications using NLX’s no-code platform. Now, everyone from individual developers to leading brands can create sophisticated multimodal experiences to engage customers with a distinct personality, in the most commonly spoken languages for consumer applications.
- Conversations that differentiate brands: Build, deploy, and analyze voice applications that solve for any use case in any industry with NLX, including contact center automations, AI assistants, and integrations with the most common digital channels (e.g., messaging apps, voice assistants).
- Low latency: Inworld voices support ~200ms latency to the first audio chunk, enabling engaging use cases for consumer applications in entertainment, hospitality, travel, retail, and more.
- Multimodal made easy: Voice and digital channels operate in real-time synchrony with NLX patented Voice+ technology, creating a natural and seamless conversational experience most like talking to a human.
- Multilingual: Build agents in 11 of the most common languages for consumer applications, including English (with its various accents), Chinese, Korean, Dutch, French, Spanish, and more.
- Scale affordably: SOTA-quality voices for just $5/M characters, which is 5% of the cost of TTS from leading labs, so you can build interactive experiences that scale and evolve with users' preferences and behaviors.
- Zero-shot voice cloning: Leverage Inworld's voice cloning capabilities to bring characters, brands, and assistants to life with emotion and personality using just 5-15 seconds of audio.
How it works
You have two options to get started…
-
Select Inworld as your preferred TTS provider within the NLX platform
‘Integrations’ and configure your voice preferences.
- Use Inworld’s API or embed Inworld voices via NLX’s voice gateway to enrich any step of the customer journey in your application. You can learn how here: NLX Integration Documentation
Interested in learning more and Inworld TTS?
Inworld Text-to-Speech Overview Inworld Text-to-Speech DocumentationInworld x NLX collaboration
Inworld and NLX share the belief that it should be easier for developers to
build high-quality, interactive consumer applications. It’s never been
easier to build a concierge for a luxury hotel, a virtual support agent, a
voice-powered onboarding flow or whatever you can imagine that brings your
brand or idea to life.
“Making quality text-to-speech accessible to
developers was a critical breakthrough to unleashing the potential of
consumer AI applications. Expressive voice is a key ingredient in embodying
the personality of a brand and making interactions with customers more
personal and engaging.”
Jean Wang, Inworld Head of Product.
“Voice and
voice-led multimodal experiences aren't just the future of AI; they're the
pathway to truly natural consumer interactions,” said Derrick Bradley, Chief
Product Officer at NLX. “Our partnership with Inworld gives NLX builders and
enterprises easy access to industry-leading voice technology, driving speed
to value when it counts most."