ResourcesIntegrationsVoices (Text-to-speech)

Inworld

What is Inworld?

Inworld develops AI products for builders of consumer applications, enabling scaled applications that grow into user needs and organically evolve through experience. This includes a text-to-speech service that makes state-of-the-art voice AI radically more accessible for developers. Inworld TTS is optimized for low-latency streaming, making it suitable for applications requiring immediate audio responses.

Overview of State-of-the-Art Inworld TTS:

Advancements in LLM-based speech models have significantly improved the quality of AI-generated speech. Inworld leverages these developments to deliver natural-sounding, emotionally expressive voices suitable for various applications, including virtual assistants, interactive games, and more. Inworld provides a comprehensive suite of features designed to meet diverse voice synthesis needs:

  • Real-Time Speech Synthesis: Inworld is engineered for real-time performance, delivering the first 2-second audio chunk in as few as 200ms. This responsiveness is critical for real-time applications such as conversational agents and interactive characters.
  • Multilingual Support: Inworld supports 11 languages, including English, Spanish, French, Korean, Chinese, and more. This multilingual capability enables developers to build applications for diverse global audiences.
  • Developer API: Inworld provides an API with comprehensive documentation, facilitating integration into various applications. The API supports real-time streaming and offers options for customizing voice parameters to suit specific use cases.

Use Cases:

Inworld TTS supports a wide range of applications:

  • Interactive Applications: Developers can create responsive voice agents for customer service, virtual assistants, and interactive characters, enhancing user engagement through natural-sounding speech.
  • Content Creation: Content creators can utilize Inworld to generate professional-grade voiceovers for videos, podcasts, and other media, streamlining the production process.
  • Education and Training: Educational platforms can employ Inworld to provide clear and expressive narration for e-learning materials, improving the learning experience for users.

Integration with Vapi:

Inworld voices are fully integrated with Vapi, giving developers an easy way to deploy expressive, real-time latency voices in their assistants.

To use Inworld voices, open your assistant in the Vapi dashboard and scroll to the Voice Configuration section. Choose Inworld as the provider, select a language and voice. Hit publish. And you’re live!

Conclusion:

Inworld offers a combination of expressive voice synthesis, real-time performance, and multilingual support, making it a valuable tool for developers seeking to enhance their applications with natural-sounding speech.