The foundational voice AI model for any interface
Real-time, customizable voice intelligence powered by empathic AI
Introducing EVI 2
Our flagship model, EVI 2, introduces a new voice-to-voice AI model architecture. EVI 2 can converse rapidly and fluently, understand a user’s tone of voice, and generate any tone of voice. It's capable of emulating a wide range of personalities, accents, and speaking styles. It can replace or integrate with LLMs.
Explore our capabilities
00/00
Design synthetic voices and personalities
Emulate the ideal personality for your use case with flexible prompting and voice modulation tools. We developed a novel voice modulation approach that allows anyone to adjust EVI 2’s 10+ base voices along a number of continuous scales, including femininity, nasality, pitch, and more.
We research foundation models and how to align them with human well-being
00/00
Build AI voices people can trust
EVI 2 excels at anticipating and adapting to users' preferences, made possible by its special training for emotional intelligence. Its pleasant and fun personality is a result of this deeper alignment with human values.
In deploying this technology, we require developers to adhere to the guidelines of The Hume Initiative, a non-profit that sets the first concrete guidelines for empathic AI.
Developer Resources
Developer Platform
Create your Hume account, get your API keys, monitor your usage, and explore our products in the interactive platform.
Developer Documentation
Explore our documentation with concise guides, hands-on tutorials, and an in-depth API reference—crafted to support your integration.
Developer Community
Join our community of developers and researchers working with Hume APIs—your go-to hub for collaboration, support, and knowledge sharing.
00/00