ProductEmpathic Voice Interface

Conversational AI with
emotional intelligence

Build voice-first AI experiences that understand and respond to human emotions. Natural, empathic conversations at scale.

Select a character to start a call

Bring your own LLM

Use any language model you want. EVI works seamlessly with Claude, GPT, Gemini, Grok, Kimi K2, Llama, and more. Switch models without changing your integration.

Your voice, your way

Choose from a curated library of expressive voices, clone any voice from a sample, or design entirely new voices from natural language descriptions. Create the perfect voice for your brand.

Real-time streaming

Start playback in milliseconds with streaming audio output. EVI begins generating speech instantly, streaming audio chunks as they're ready. Perfect for real-time applications where every millisecond counts.

~300msTime to first byte

Try it yourself

Experience EVI firsthand in our interactive playground. Configure your agent, test different voices, and see how emotional intelligence transforms conversations—no code required.

Features

Everything you need for voice AI

Interruptibility

Users can interrupt at any time, just like real conversations.

Pause responses

Programmatically pause and resume responses at any moment.

Resume chats

Pick up conversations right where they left off with full context.

Chat history

Access complete transcripts with timestamps and emotion data.

Dynamic variables

Inject real-time data like user names, account info, and prices.

Context injection

Add context mid-conversation for RAG and knowledge bases.

Tool use

Connect to your APIs for appointments, orders, and more.

Audio reconstruction

Reconstruct complete audio from any conversation on demand.

For Developers

Build voice experiences in minutes

Integrate EVI into your application with just a few lines of code. Full SDK support for React, TypeScript, Python, .NET, Swift, and more.

index.ts

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

Enterprise Ready

Built for business

Deploy with confidence knowing EVI meets the security, compliance, and scale requirements of enterprise applications.

Contact sales

SOC 2 Type II

Enterprise-grade security with industry-leading practices.

HIPAA compliant

Build healthcare applications with confidence.

Enterprise plans

Custom SLAs, dedicated support, and volume pricing.

FAQ

Frequently asked questions

EVI (Empathic Voice Interface) is Hume's voice AI that understands and responds to human emotions in real-time. It combines speech recognition, emotion detection, and natural language processing to create more natural, empathic conversations.

Start building with EVI

Create voice experiences that truly understand your users. Free to start, scales with you.

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