For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
WebsiteStatusSupportDashboard
DocumentationAPI ReferenceMCPSDKsCLI (new)What's New?
DocumentationAPI ReferenceMCPSDKsCLI (new)What's New?
  • Get started
    • Introduction
    • Phone calls
    • Web calls
    • Vapi Guides
    • Composer
    • CLI quickstart
  • Assistants
    • Quickstart
    • Tools
    • Custom keywords
    • Custom voices
    • Custom transcriber
    • Custom TTS
  • Observability
    • Boards
  • Squads
    • Quickstart
    • Overview
    • Handoff tool
    • Passing data between assistants
  • Best practices
    • Prompting guide
    • Debugging voice agents
    • Enterprise environments (DEV/UAT/PROD)
    • IVR navigation
  • Phone numbers
    • Free Vapi number
    • Inbound SMS
    • Phone Number Hooks
  • Calls
    • Call end reasons
    • Troubleshoot call errors
  • Outbound Campaigns
    • Quickstart
    • Overview
  • Chat
    • Quickstart
    • Streaming
    • Non-streaming
    • OpenAI compatibility
    • Session management
    • Variable substitution
    • SMS chat
    • Web widget
    • Webhooks
  • Workflows
    • Quickstart
    • Overview
      • FAQ
          • Vapi Voices
          • ElevenLabs
          • PlayHT
          • Azure
          • OpenAI
          • Cartesia
          • LMNT
          • Minimax
          • RimeAI
          • Deepgram
          • Inworld
      • Support
LogoLogo
WebsiteStatusSupportDashboard
ResourcesIntegrationsVoices (Text-to-speech)

Inworld

Was this page helpful?
Edit this page
Previous

OpenAI

What is OpenAI?
Next
Built with

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.