\n\t\t\t\t

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More<\/em><\/p>\n\n\n\n

\n<\/div>
New York-based AI startup Hume has unveiled its latest Empathic Voice Interface (EVI) conversational AI model, EVI 3 (pronounced \u201cEvee\u201d Three, like the Pok\u00e9mon character), targeting everything from powering customer support systems and health coaching to immersive storytelling and virtual companionship.<\/p>\n\n\n\n
EVI 3 lets users create their own voices by talking to the model (it\u2019s voice-to-voice\/speech-to-speech), and aims to set a new standard for naturalness, expressiveness, and \u201cempathy\u201d according to Hume \u2014 that is, how users perceive the model\u2019s understanding of their emotions and its ability to mirror or adjust its own responses, in terms of tone and word choice. <\/p>\n\n\n\n
Designed for businesses, developers, and creators, EVI 3 expands on Hume\u2019s previous voice models by offering more sophisticated customization, faster responses, and enhanced emotional understanding.<\/p>\n\n\n\n
Individual users can interact with it today through Hume\u2019s live demo on its website and iOS app, but developer access through Hume\u2019s proprietary application programming interface (API) is said to be made available in \u201cthe coming weeks,\u201d as a blog post from the company states.<\/p>\n\n\n\n
At that point, developers will be able to embed EVI 3 into their own customer service systems, creative projects, or virtual assistants \u2014 for a price (see below).<\/p>\n\n\n\n
My own usage of the demo allowed me to create a new, custom synthetic voice in seconds based on qualities I described to it \u2014 a mix of warm and confident, and a masculine tone. Speaking to it felt more naturalistic and easy than other AI models and certainly the stock voices from legacy tech leaders such Apple with Siri and Amazon with Alexa. <\/p>\n\n\n\n
Wh<\/strong>at developers and businesses should know about EVI 3<\/h2>\n\n\n\n
Hume\u2019s EVI 3 is built for a range of uses\u2014from customer service and in-app interactions to content creation in audiobooks and gaming. <\/p>\n\n\n\n
It allows users to specify precise personality traits, vocal qualities, emotional tone, and conversation topics.<\/p>\n\n\n\n
This means it can produce anything from a warm, empathetic guide to a quirky, mischievous narrator\u2014down to requests like \u201ca squeaky mouse whispering urgently in a French accent about its scheme to steal cheese from the kitchen.\u201d<\/p>\n\n\n\n
EVI 3\u2019s core strength lies in its ability to integrate emotional intelligence directly into voice-based experiences. <\/p>\n\n\n\n
Unlike traditional chatbots or voice assistants that rely heavily on scripted or text-based interactions, EVI 3 adapts to how people naturally speak \u2014 picking up on pitch, prosody, pauses, and vocal bursts to create more engaging, humanlike conversations.<\/p>\n\n\n\n
However, one big feature Hume\u2019s models currently lack \u2014 and which is offered by rivals open source and proprietary, such as ElevenLabs \u2014 is voice cloning, or the rapid replication of a user\u2019s or other voice, such as a company CEO.<\/p>\n\n\n\n
Yet Hume has indicated it will add such a capability to its Octave text-to-speech model, as it is noted as \u201ccoming soon\u201d on Hume\u2019s website, and prior reporting by yours truly on the company found it will allow users to replicate voices from as little as five seconds of audio.<\/p>\n\n\n\n
Hume has stated it\u2019s prioritizing safeguards and ethical considerations before making this feature broadly available. Currently, this cloning capability is not available in EVI itself, with Hume emphasizing flexible voice customization instead.<\/p>\n\n\n\n
Internal benchmarks show users prefer EVI 3 to OpenAI\u2019s GPT-4o voice model<\/h2>\n\n\n\n
According to Hume\u2019s own tests with 1,720 users, EVI 3 was preferred over OpenAI\u2019s GPT-4o in every category evaluated: naturalness, expressiveness, empathy, interruption handling, response speed, audio quality, voice emotion\/style modulation on request, and emotion understanding on request (the \u201con request\u201d features are covered in \u201cinstruction following\u201d seen below). <\/p>\n\n\n\n
It also usually bested Google\u2019s Gemini model family and the new open source AI model firm Sesame from former Oculus co-creator Brendan Iribe.<\/p>\n\n\n\n
$\"\"$ <\/figure>\n\n\n\n
$\"\"$ <\/figure>\n\n\n\n
\n
$\"\"$ <\/figure>\n<\/figure>\n\n\n\n
It also boasts lower latency (~300 milliseconds), robust multilingual support (English and Spanish, with more languages coming), and effectively unlimited custom voices. As Hume writes on its website (see screenshot immediately below):<\/p>\n\n\n\n
$\"\"$ <\/figure>\n\n\n\n
Key capabilities include:<\/p>\n\n\n\n
\n
Prosody generation<\/strong> and expressive text-to-speech with modulation.<\/li>\n\n\n\n
Interruptibility<\/strong>, enabling dynamic conversational flow.<\/li>\n\n\n\n
In-conversation voice customizability<\/strong>, so users can adjust speaking style in real time.<\/li>\n\n\n\n
API-ready architecture<\/strong> (coming soon), so developers can integrate EVI 3 directly into apps and services.<\/li>\n<\/ul>\n\n\n\n
Pricing and developer access<\/h2>\n\n\n\n
Hume offers flexible, usage-based pricing across its EVI, Octave TTS, and Expression Measurement APIs. <\/p>\n\n\n\n
While EVI 3\u2019s specific API pricing has not been announced yet (marked as TBA), the pattern suggests it will be usage-based, with enterprise discounts available for large deployments. <\/p>\n\n\n\n
For reference, EVI 2 is priced at $0.072 per minute \u2014 30% lower than its predecessor, EVI 1 ($0.102\/minute).<\/p>\n\n\n\n
For creators and developers working with text-to-speech projects, Hume\u2019s Octave TTS plans range from a free tier (10,000 characters of speech, ~10 minutes of audio) to enterprise-level plans. Here\u2019s the breakdown:<\/p>\n\n\n\n
\n
Free<\/strong>: 10,000 characters, unlimited custom voices, $0\/month<\/li>\n\n\n\n
Starter<\/strong>: 30,000 characters (~30 minutes), 20 projects, $3\/month<\/li>\n\n\n\n
Creator<\/strong>: 100,000 characters (~100 minutes), 1,000 projects, usage-based overage ($0.20\/1,000 characters), $10\/month<\/li>\n\n\n\n
Pro<\/strong>: 500,000 characters (~500 minutes), 3,000 projects, $0.15\/1,000 extra, $50\/month<\/li>\n\n\n\n
Scale<\/strong>: 2,000,000 characters (~2,000 minutes), 10,000 projects, $0.13\/1,000 extra, $150\/month<\/li>\n\n\n\n
Business<\/strong>: 10,000,000 characters (~10,000 minutes), 20,000 projects, $0.10\/1,000 extra, $900\/month<\/li>\n\n\n\n
Enterprise<\/strong>: Custom pricing and unlimited usage<\/li>\n<\/ul>\n\n\n\n
For developers working on real-time voice interactions or emotional analysis, Hume also offers a Pay as You Go plan with $20 in free credits and no upfront commitment. High-volume enterprise customers can opt for a dedicated Enterprise plan featuring dataset licenses, on-premises solutions, custom integrations, and advanced support.<\/p>\n\n\n\n
Hume\u2019s history of emotive AI voice models<\/h2>\n\n\n\n
Founded in 2021 by Alan Cowen, a former researcher at Google DeepMind, Hume aims to bridge the gap between human emotional nuance and AI interaction. <\/p>\n\n\n\n
The company trained its models on an expansive dataset drawn from hundreds of thousands of participants worldwide\u2014capturing not just speech and text, but also vocal bursts and facial expressions.<\/p>\n\n\n\n
\u201cEmotional intelligence includes the ability to infer intentions and preferences from behavior. That\u2019s the very core of what AI interfaces are trying to achieve,\u201d Cowen told VentureBeat. Hume\u2019s mission is to make AI interfaces more responsive, humanlike, and ultimately more useful\u2014whether that\u2019s helping a customer navigate an app or narrating a story with just the right blend of drama and humor.<\/p>\n\n\n\n
In early 2024, the company launched EVI 2, which offered 40% lower latency and 30% reduced pricing compared to EVI 1, alongside new features like dynamic voice customization and in-conversation style prompts. <\/p>\n\n\n\n
February 2025 saw the debut of Octave, a text-to-speech engine for content creators capable of adjusting emotions at the sentence level with text prompts.<\/p>\n\n\n\n
With EVI 3 now available for hands-on exploration and full API access just around the corner, Hume hopes to allow developers and creators to reimagine what\u2019s possible with voice AI.<\/p>\n
\n
\n
Daily insights on business use cases with VB Daily<\/strong><\/p>\n
If you want to impress your boss, VB Daily has you covered. We give you the inside scoop on what companies are doing with generative AI, from regulatory shifts to practical deployments, so you can share insights for maximum ROI.<\/p>\n
Read our Privacy Policy<\/p>\n
\n\t\t\t\t\tThanks for subscribing. Check out more VB newsletters here.\n\t\t\t\t<\/p>\n
An error occured.<\/p>\n<\/p><\/div>\n
\n\t\t\t\t\t $\"\"\/$ \n\t\t\t\t<\/div>\n<\/p><\/div>\n<\/div>\t\t\t<\/div>\r\n
\r\n
Source link <\/a>","protected":false},"excerpt":{"rendered":"
Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More New York-based AI startup Hume has unveiled its latest Empathic Voice Interface (EVI) conversational AI model, EVI 3 (pronounced \u201cEvee\u201d Three, like the Pok\u00e9mon character), targeting everything from powering customer support systems and health coaching to […]<\/p>\n","protected":false},"author":1,"featured_media":1864,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[33],"tags":[],"class_list":["post-1863","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-automation"],"aioseo_notices":[],"jetpack_featured_media_url":"https:\/\/violethoward.com\/new\/wp-content\/uploads\/2025\/05\/cfr0z3n_minimalist_flat_polygonal_basic_shapes_retro_modern_col_54f82d10-cd96-4390-ad57-eb1b220e3c3a.png","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/violethoward.com\/new\/wp-json\/wp\/v2\/posts\/1863","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/violethoward.com\/new\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/violethoward.com\/new\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/violethoward.com\/new\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/violethoward.com\/new\/wp-json\/wp\/v2\/comments?post=1863"}],"version-history":[{"count":0,"href":"https:\/\/violethoward.com\/new\/wp-json\/wp\/v2\/posts\/1863\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/violethoward.com\/new\/wp-json\/wp\/v2\/media\/1864"}],"wp:attachment":[{"href":"https:\/\/violethoward.com\/new\/wp-json\/wp\/v2\/media?parent=1863"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/violethoward.com\/new\/wp-json\/wp\/v2\/categories?post=1863"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/violethoward.com\/new\/wp-json\/wp\/v2\/tags?post=1863"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}