Be part of our each day and weekly newsletters for the most recent updates and unique content material on industry-leading AI protection. Learn More
New York-based AI startup Hume has unveiled its latest Empathic Voice Interface (EVI) conversational AI model, EVI 3 (pronounced “Evee” Three, just like the Pokémon character), focusing on every little thing from powering buyer assist programs and well being teaching to immersive storytelling and digital companionship.
EVI 3 lets customers create their very own voices by speaking to the mannequin (it’s voice-to-voice/speech-to-speech), and goals to set a brand new normal for naturalness, expressiveness, and “empathy” in accordance with Hume — that’s, how customers understand the mannequin’s understanding of their feelings and its potential to reflect or regulate its personal responses, by way of tone and phrase alternative.
Designed for companies, builders, and creators, EVI 3 expands on Hume’s earlier voice fashions by providing extra refined customization, sooner responses, and enhanced emotional understanding.
Particular person customers can work together with it at present via Hume’s live demo on its website and iOS app, however developer entry via Hume’s proprietary utility programming interface (API) is claimed to be made accessible in “the approaching weeks,” as a blog post from the company states.
At that time, builders will have the ability to embed EVI 3 into their very own customer support programs, artistic tasks, or digital assistants — for a value (see beneath).
My very own utilization of the demo allowed me to create a brand new, customized artificial voice in seconds primarily based on qualities I described to it — a mixture of heat and assured, and a masculine tone. Talking to it felt extra naturalistic and simple than different AI fashions and positively the inventory voices from legacy tech leaders such Apple with Siri and Amazon with Alexa.
What builders and companies ought to find out about EVI 3
Hume’s EVI 3 is constructed for a spread of makes use of—from customer support and in-app interactions to content material creation in audiobooks and gaming.
It permits customers to specify exact persona traits, vocal qualities, emotional tone, and dialog matters.
This implies it will possibly produce something from a heat, empathetic information to a unusual, mischievous narrator—all the way down to requests like “a squeaky mouse whispering urgently in a French accent about its scheme to steal cheese from the kitchen.”
EVI 3’s core power lies in its potential to combine emotional intelligence instantly into voice-based experiences.
In contrast to conventional chatbots or voice assistants that rely closely on scripted or text-based interactions, EVI 3 adapts to how folks naturally converse — selecting up on pitch, prosody, pauses, and vocal bursts to create extra partaking, humanlike conversations.
Nonetheless, one large characteristic Hume’s fashions at the moment lack — and which is obtainable by rivals open supply and proprietary, reminiscent of ElevenLabs — is voice cloning, or the fast replication of a consumer’s or different voice, reminiscent of an organization CEO.
But Hume has indicated it would add such a functionality to its Octave text-to-speech mannequin, as it’s famous as “coming quickly” on Hume’s web site, and prior reporting by yours really on the corporate discovered it would enable customers to duplicate voices from as little as 5 seconds of audio.
Hume has acknowledged it’s prioritizing safeguards and moral concerns earlier than making this characteristic broadly accessible. Presently, this cloning functionality will not be accessible in EVI itself, with Hume emphasizing versatile voice customization as a substitute.
Inside benchmarks present customers want EVI 3 to OpenAI’s GPT-4o voice mannequin
In response to Hume’s personal checks with 1,720 customers, EVI 3 was most popular over OpenAI’s GPT-4o in each class evaluated: naturalness, expressiveness, empathy, interruption dealing with, response pace, audio high quality, voice emotion/model modulation on request, and emotion understanding on request (the “on request” options are coated in “instruction following” seen beneath).
It additionally often bested Google’s Gemini mannequin household and the brand new open supply AI model firm Sesame from former Oculus co-creator Brendan Iribe.
It additionally boasts decrease latency (~300 milliseconds), strong multilingual assist (English and Spanish, with extra languages coming), and successfully limitless customized voices. As Hume writes on its web site (see screenshot instantly beneath):
Key capabilities embody:
- Prosody era and expressive text-to-speech with modulation.
- Interruptibility, enabling dynamic conversational circulation.
- In-conversation voice customizability, so customers can regulate talking model in actual time.
- API-ready structure (coming quickly), so builders can combine EVI 3 instantly into apps and providers.
Pricing and developer entry
Hume provides versatile, usage-based pricing throughout its EVI, Octave TTS, and Expression Measurement APIs.
Whereas EVI 3’s particular API pricing has not been introduced but (marked as TBA), the sample suggests will probably be usage-based, with enterprise reductions accessible for giant deployments.
For reference, EVI 2 is priced at $0.072 per minute — 30% decrease than its predecessor, EVI 1 ($0.102/minute).
For creators and builders working with text-to-speech tasks, Hume’s Octave TTS plans vary from a free tier (10,000 characters of speech, ~10 minutes of audio) to enterprise-level plans. Right here’s the breakdown:
- Free: 10,000 characters, limitless customized voices, $0/month
- Starter: 30,000 characters (~half-hour), 20 tasks, $3/month
- Creator: 100,000 characters (~100 minutes), 1,000 tasks, usage-based overage ($0.20/1,000 characters), $10/month
- Professional: 500,000 characters (~500 minutes), 3,000 tasks, $0.15/1,000 further, $50/month
- Scale: 2,000,000 characters (~2,000 minutes), 10,000 tasks, $0.13/1,000 further, $150/month
- Enterprise: 10,000,000 characters (~10,000 minutes), 20,000 tasks, $0.10/1,000 further, $900/month
- Enterprise: Customized pricing and limitless utilization
For builders engaged on real-time voice interactions or emotional evaluation, Hume additionally provides a Pay as You Go plan with $20 in free credit and no upfront dedication. Excessive-volume enterprise prospects can go for a devoted Enterprise plan that includes dataset licenses, on-premises options, customized integrations, and superior assist.
Hume’s historical past of emotive AI voice fashions
Based in 2021 by Alan Cowen, a former researcher at Google DeepMind, Hume goals to bridge the hole between human emotional nuance and AI interplay.
The corporate educated its fashions on an expansive dataset drawn from a whole bunch of 1000’s of members worldwide—capturing not simply speech and textual content, but in addition vocal bursts and facial expressions.
“Emotional intelligence contains the flexibility to deduce intentions and preferences from conduct. That’s the very core of what AI interfaces are attempting to realize,” Cowen advised VentureBeat. Hume’s mission is to make AI interfaces extra responsive, humanlike, and in the end extra helpful—whether or not that’s serving to a buyer navigate an app or narrating a narrative with simply the fitting mix of drama and humor.
In early 2024, the corporate launched EVI 2, which supplied 40% decrease latency and 30% lowered pricing in comparison with EVI 1, alongside new options like dynamic voice customization and in-conversation model prompts.
February 2025 noticed the debut of Octave, a text-to-speech engine for content material creators able to adjusting feelings on the sentence degree with textual content prompts.
With EVI 3 now accessible for hands-on exploration and full API entry simply across the nook, Hume hopes to permit builders and creators to reimagine what’s potential with voice AI.
Source link
