Emotional intelligence for any application
Measure expression along with language. Build a voice interface. Optimize for happiness.
Voice-to-voice AI with EQ
Conversation powered by a new form of empathic AI
Hume's EVI is an API powered by our empathic large language model (eLLM), which understands and emulates tones of voice, word emphasis and more to optimize human-AI interaction.
A universal voice interface
a single API for transcription, frontier LLMs, and text-to-speech.
End-of-turn detection
uses your tone of voice for state-of-the-art end-of-turn detection, eliminating awkward overlaps.
Interruptibility
stops speaking when interrupted and starts listening, just like a human.
Responds to expression
understands the natural ups and downs in pitch & tone used to convey meaning beyond words.
Expressive TTS
generates the right tone of voice to respond with natural, expressive speech.
Aligned with your application
learns from users' reactions to self-improve by optimizing for happiness and satisfaction.
Give your application a voice in minutes
Build an interface that's 4x faster than typing and twice as informative.
Measure emotional expression with unmatched precision
One API, four modalities, hundreds of dimensions of emotion.
Voice models
Voice models
Image & video models
Speech Prosody
Image & video models
Voice models
Image & video models
Speech Prosody
Voice models
Image & video models
Speech Prosody
Voice models
Image & video models
Our models are built on 10+ years of research, millions of proprietary data points, and over 30 publications in leading journals.
Try in PlaygroundUse cases
AI Research / Services
The next generation of search, recommendation, and content generation
Social Networks
Toxicity detection; health/well-being monitoring; relationship
Call Center Analytics
Call triaging (e.g., frustration); emergency detection (e.g., pain); training
Embedded Devices
Social robots, Al baby monitors; Al dash cams; warehouse safety
Brand / Financial Analysis
Sentiment analysis for market forecasting and brand sentiment research
Creative Tools
Character animation; content generation, editing, and curation
Digital Assistants
Conversational Al (e.g., back channeling; optimization (e.g., t frustration)
UX / CX Research
Sentiment analysis of user interviews and tests
Education / Coaching
Focus/boredom detection; student well-being; leadership coaching
Research Labs
Clinical research and psychology
Sales / Meeting Analytics
Sales rep coaching; analyzing customer engagement and sentiment
Health & Wellness
Clinical diagnosis (e.g., depression, autism); patient monitoring, therapy.
AI Research / Services
The next generation of search, recommendation, and content generation
Social Networks
Toxicity detection; health/well-being monitoring; relationship
Call Center Analytics
Call triaging (e.g., frustration); emergency detection (e.g., pain); training
Embedded Devices
Social robots, Al baby monitors; Al dash cams; warehouse safety
Brand / Financial Analysis
Sentiment analysis for market forecasting and brand sentiment research
Creative Tools
Character animation; content generation, editing, and curation
Digital Assistants
Conversational Al (e.g., back channeling; optimization (e.g., t frustration)
UX / CX Research
Sentiment analysis of user interviews and tests
Education / Coaching
Focus/boredom detection; student well-being; leadership coaching
Research Labs
Clinical research and psychology
Sales / Meeting Analytics
Sales rep coaching; analyzing customer engagement and sentiment
Health & Wellness
Clinical diagnosis (e.g., depression, autism); patient monitoring, therapy.
Predict preferences more accurately than any LLM
Sample custom models
Screen and monitor health and wellness more accurately.
Depressed Mood
video
Health & Wellness
Infers the mood of vloggers with a 2.4x lower error rate by incorporating expression compared to language alone.
Flag toxic speech more reliably to improve moderation.
Toxic Speech
audio
Moderation
Identifies toxic speech by online gamers with a 36% lower error rate than a language-only model.
Decipher signs of customer satisfaction and frustration.
Call Quality
audio
Customer service
Uses the voice to classify the quality of customer support calls with 2.8x fewer errors than language alone in data from Lawyer.com.
00/00
Why Hume?
Our models are used to improve how technology affects human well-being by Fortune 500 companies, startups, research institutions, and hospitals.
Grounded in rigorous science
Our models, based on extensive empirical research, utilize millions of experimentally-controlled expressions from dozens of countries and millions of hours of human interaction to enhance the products you build.
Adaptable and easy to customize
Generate customizable insights and experiences with our APIs. Easily integrate them into your product with a few lines of code. Our API is as adaptable as it is powerful - a general-purpose tool for building empathic user experiences in many different verticals.
Backed by support from ideation to implementation
For many customers, empathic AI is new. Hume and its growing partner base is dedicated to helping you build solutions that generate meaningful business value.
Unparalleled insights, state-of-the-art results
We measure hundreds of dimensions of expression in vocal tones, speech prosody, facial expressions, and more. Our insights are much more accurate than what language alone can capture.