Hume EVI
by Hume AI
Empathic Voice Interface — voice AI that reads and responds to emotion in speech.
Looking at Hume EVI? Try this first.
Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min
TL;DR
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.
Watch out for: Emotion claims should be validated for your population; English-led model coverage.
Features
| Speaker diarization | No |
| Word-level timestamps | No |
| Streaming / real-time | No |
| Languages supported | None |
| HIPAA eligible | No |
Hume EVI vs Whipscribe
| Feature | Hume EVI | Whipscribe |
|---|---|---|
| Category | Transcription APIs | Transcription APIs |
| Pricing | Not verified | $4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup |
| Speaker diarization | Not verified | Yes |
| Word timestamps | Not verified | Yes |
| Streaming | Not verified | No |
| Languages | — | 99 |
| Platforms | Web, Cloud, API | Web, 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.