Hume EVI

by Hume AI

Empathic Voice Interface — voice AI that reads and responds to emotion in speech.

TL;DR

Empathic Voice Interface — voice AI that reads and responds to emotion in speech.

Best for wellness, coaching, and companion apps where tone matters as much as words. Pricing: see vendor pricing.

Category
Transcription APIs
License
Stars
Last push
Pricing
see vendor pricing
Platforms
Web, Cloud, API

What it is

Hume's Empathic Voice Interface (EVI) is a streaming voice API that returns transcription plus emotional prosody scores and generates speech tuned to user affect. Developers integrate EVI over WebSocket with their own logic or use Hume's hosted conversational LLM. EVI competes with OpenAI Realtime by emphasizing emotional context over pure latency.

Best for: Wellness, coaching, and companion apps where tone matters as much as words.
Watch out for: Emotion claims should be validated for your population; English-led model coverage.

Features

Speaker diarizationNo
Word-level timestampsNo
Streaming / real-timeNo
Languages supportedNone
HIPAA eligibleNo

Hume EVI vs Whipscribe

FeatureHume EVIWhipscribe
CategoryTranscription APIsTranscription APIs
Pricingsee vendor pricingfree beta
Speaker diarizationYes
Word timestampsYes
StreamingNo
Languages99
PlatformsWeb, Cloud, APIWeb, API, MCP

Alternatives to Hume EVI

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.