Hume EVI (Empathic Voice + Prosody)

by Hume AI

Hume's voice-AI platform with prosody/expression analysis bundled with transcription.

TL;DR

Hume's voice-AI platform with prosody/expression analysis bundled with transcription.

Best for voice-agent and wellbeing products that need expression/prosody features alongside transcripts. Pricing: per-minute (see Hume pricing).

Category
Products
License
Stars
Last push
Pricing
per-minute (see Hume pricing)
Platforms
API

What it is

Hume AI offers EVI (Empathic Voice Interface) — a voice-agent platform with native ASR + LLM + TTS — plus standalone Prosody and Speech-Prosody models that label vocal expression along multi-dimensional axes. The platform exposes word-level transcription and frame-by-frame expression scoring over WebSocket. Common use cases: AI companions, wellbeing apps, qualitative research. Best fit: voice-agent and wellbeing products that need expression/prosody features alongside transcripts. Caveats: expression/prosody outputs are interpretive — treat with care for high-stakes decisions. Pricing as listed: per-minute (see Hume pricing). Feature flags from vendor docs: word-level timestamps, streaming. Directory tags: voice-intel, emotion-analysis, voice-agent. Last vendor-page check: 2026-05-12.

Best for: Voice-agent and wellbeing products that need expression/prosody features alongside transcripts.
Watch out for: Expression/prosody outputs are interpretive — treat with care for high-stakes decisions.

Install / use

Hume Empathic Voice Interface (EVI) WebSocket

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeYes
Languages supportedNone
HIPAA eligibleNo

Hume EVI (Empathic Voice + Prosody) vs Whipscribe

FeatureHume EVI (Empathic Voice + Prosody)Whipscribe
CategoryProductsTranscription APIs
Pricingper-minute (see Hume pricing)free beta
Speaker diarizationYes
Word timestampsYesYes
StreamingYesNo
Languages99
PlatformsAPIWeb, API, MCP

Alternatives to Hume EVI (Empathic Voice + Prosody)

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.