×
Hume Launches ‘EVI 2’ AI Voice Model with Emotional Responsiveness
Written by
Published on
Join our daily newsletter for breaking news, product launches and deals, research breakdowns, and other industry-leading AI coverage
Join Now

Hume’s EVI 2: A leap forward in AI voice technology: Hume, an AI startup, has unveiled Empathic Voice Interface 2 (EVI 2), a significant upgrade to its AI voice model and API, offering enhanced naturalness, emotional responsiveness, and customizability.

Key improvements and features: EVI 2 brings substantial enhancements over its predecessor, addressing critical aspects of AI voice interaction.

  • The new version boasts a 40% reduction in latency, with response times ranging from 500 to 800 milliseconds, greatly improving real-time conversation capabilities.
  • EVI 2 demonstrates improved emotional intelligence, better understanding and responding to the emotional context of user inputs.
  • The system now allows for customizable voices, enabling adjustments to voice parameters without the need for voice cloning.
  • Users can modify the AI’s speaking style dynamically during conversations through in-conversation prompts.
  • While currently supporting English, EVI 2 has plans to expand its multilingual capabilities in the future.

Technical advancements: The core technology behind EVI 2 represents a significant step forward in AI voice processing.

  • EVI 2 converts audio signals directly into tokens, a method similar to OpenAI’s GPT-4o, potentially improving efficiency and accuracy in voice recognition and processing.
  • The system allows for direct integration within apps, eliminating the need for separate voice assistants and potentially streamlining user experiences.

Cost-effectiveness and pricing: Hume has made EVI 2 more accessible to developers and businesses through competitive pricing.

  • The new version is priced at $0.072 per minute, marking a 30% reduction from its predecessor.
  • Enterprise users can benefit from volume discounts, making it more attractive for large-scale implementations.

Additional offerings and APIs: Alongside EVI 2, Hume provides complementary tools to enhance voice and expression analysis.

  • The Expression Measurement API, starting at $0.0276 per minute for video with audio, measures various aspects of communication including speech prosody and facial expressions.
  • Hume offers a Custom Models API with free model training, with inference costs matching those of the Expression Measurement API.

Future roadmap and industry positioning: Hume has outlined ambitious plans for EVI 2’s future development and market positioning.

  • The company aims to expand language support, further improve the naturalness of voice outputs, and enhance overall reliability.
  • Hume is positioning EVI 2 to work seamlessly with other large language models and integrate with tools like web search, potentially broadening its applicability and market reach.

Implications for AI voice technology: EVI 2’s launch signals a potential shift in the AI voice interaction landscape, with implications for various industries.

  • The improved emotional responsiveness and customizability could lead to more natural and engaging AI-human interactions in customer service, healthcare, and entertainment sectors.
  • The reduced latency and costs may accelerate the adoption of AI voice technologies in a wider range of applications and businesses.
  • As EVI 2 integrates with other language models and tools, it could contribute to the development of more sophisticated and versatile AI assistants.
Who needs GPT-4o Voice Mode? Hume’s EVI 2 is here with emotionally inflected voice AI and API

Recent News

Grok stands alone as X restricts AI training on posts in new policy update

X explicitly bans third-party AI companies from using tweets for model training while still preserving access for its own Grok AI.

Coming out of the dark: Shadow AI usage surges in enterprise IT

IT leaders report 90% concern over unauthorized AI tools, with most organizations already suffering negative consequences including data leaks and financial losses.

Anthropic CEO opposes 10-year AI regulation ban in NYT op-ed

As AI capabilities rapidly accelerate, Anthropic's chief executive argues for targeted federal transparency standards rather than blocking state-level regulation for a decade.