ProductExpression Measurement

Measure what words can't capture

A comprehensive suite of models for analyzing human expression across face and voice. Detect nuanced emotions with scientific precision using the same methods trusted by researchers worldwide.

Built on Science

Decades of research, one platform

#1

in naturalness and expressivity

600+

tags

of emotions and voice characteristics detected

250

ms

speech LLM latency

Model Suite

Seven specialized models, one unified API

Each model is purpose-built for a specific aspect of expression analysis. Use them individually or combine them for comprehensive multimodal understanding.

Speech Prosody

Analyze rhythm, stress, and intonation to understand emotional undertones.

audio

Vocal Expression

Detect emotions from voice timbre, resonance, and vocal quality.

audio

Vocal Bursts

Recognize laughter, sighs, gasps, and other non-verbal vocalizations.

audio

FACS 2.0

Industry-standard Facial Action Coding System for precise AU detection.

visual

Dynamic Reaction

Track how expressions change over time in response to stimuli.

visualaudio

Facial Expression

Comprehensive emotion recognition across cultures and lighting conditions.

visual

Language

Analyze text for emotional expression, sentiment, and content safety.

text

Scientific Foundation

Built on decades of research

Our models are grounded in peer-reviewed emotion science, developed in collaboration with leading researchers in psychology, affective computing, and machine learning.

View our research

Peer-reviewed methods

Built on 53+ publications in affective science and validated by independent researchers.

Neuroscience-informed

Models designed around how the brain actually processes and expresses emotion.

Validated accuracy

Benchmarked against gold-standard datasets with documented performance metrics.

Continuous updates

Regularly refined with new research findings and expanded training data.

For Developers

Simple API, powerful results

Send images, audio, or video to our API and receive structured emotion predictions in milliseconds. Full SDK support for Python, TypeScript, and more.

analyze.py
from hume import HumeClient
from hume.expression_measurement.batch import Face, Models

client = HumeClient(api_key="YOUR_API_KEY")

job_id = client.expression_measurement.batch.start_inference_job(
models=Models(face=Face()),
urls=["https://example.com/media.mp4"],
)

predictions = client.expression_measurement.batch.get_job_predictions(
id=job_id
)

Case Studies

See what others are building

View all case studies
Screenshot 2025 04 07 at 4.25.08 Pm 3

Niantic Spatial × Hume AI: Creating Interactive & Spatially Aware AI Companions

In partnership with Snap Inc. (hardware) and Hume AI (voice), Niantic Spatial has developed location-aware companions for Spectacles, blending Snap Inc.’s AR glasses, Niantic Spatial’s Large Geospatial Model, and Hume’s Empathic Voice Interface (EVI) for natural, emotionally intelligent conversation. Niantic Spatial, the team pioneering AI that understands the physical world, is showcasing a compelling glimpse of what can happen when spatial intelligence and augmented reality meet.

Read case study
Gaf Logo

GAF Powers Professional Training with Hume’s Text-to-Speech

To support their extensive training programs and marketing initiatives, GAF leverages Hume's text-to-speech technology to make internal training videos and marketing voiceovers. Our partnership addresses several key needs: Professional training content: Delivering consistent, high-quality audio for thousands of contractors and employees. Marketing collateral: Producing engaging voiceovers for promotional content and product demonstrations. Scalable production: Generating content without the logistics and cost of traditional voice recording. Hume's voice design also proved ideal for GAF. The platform's natural, expressive voices maintain the authoritative yet approachable tone that GAF needs to communicate with contractors, retailers, and customers. Unlike synthetic voices that can sound robotic or overly casual, Hume's TTS technology delivers the polished, trustworthy quality expected from an industry leader.

Read case study
Coconot Logo 3.0

Hume AI powers conversational learning with Coconote

While traditional note-taking apps require students to manually scroll and search through content, Coconote is creating interactive study experiences through conversational AI. Coconote’s voice chat feature, powered by Hume's EVI, helps users transform static notes into dynamic conversations. Students can: Ask natural questions about their lecture content Receive contextual explanations referencing specific notes, and Engage in quiz-style conversations for active learning—all through natural voice interaction.

Read case study

FAQ

Frequently asked questions

Expression Measurement is Hume's suite of AI models for analyzing human emotion from face and voice. It detects nuanced emotional expressions with scientific precision, using the same methodologies trusted by researchers worldwide.

Ready to measure expression?

Start analyzing emotions from face and voice with our suite of research-grade models. Free tier available.

Stay in the loop

Get the latest on empathic AI research, product updates, and company news.

Join the community

Connect with other developers, share projects, and get help from the team.

Join our Discord