Hume EVI 3 / EVI 4 mini (speech-to-speech)
EVI 3 is English-only and can answer without an external LLM ('quick responses'); EVI 4 mini is multilingual but requires a supplemental LLM. Both share the same WebSocket; version is chosen in the EVI configuration. Full EVI 4 not launched as of 2026-09-29 (not on Hume blog). EVI 1/2 are older generations.
- Input
- audio, text
- Output
- audio, text
- License
- proprietary
- Pricing
- per minute: $0.06 (per minute overage on Free/Pro ($0.07 Starter/Creator, $0.05 Scale, $0.04 Business); plans include monthly minutes) source
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Hume API (EVI WebSocket) | EVI version 3 or 4-mini (set in EVI config) | wss://api.hume.ai/v0/evi/chat | docs |
| Web app | — | platform.hume.ai | — |
Notable capabilities (2)
- Empathic voice interface with any prompted voice: EVI 3 (2025-05-29) is a speech-to-speech foundation model that can speak in any of 100,000+ custom voices created via prompting, with inferred personality; ~1.2 s practical end-of-speech-to-response latency at launch. source
- EVI 4 mini: Octave 2 voice in 11 languages: EVI 4 mini (announced with Octave 2 on 2025-10-01) brings Octave 2 to the speech-to-speech API in 11 languages but must be paired with an external LLM (Anthropic, OpenAI, Google, Fireworks...) until the full EVI 4 ships. source
Hume's Empathic Voice Interface for real-time voice agents.
Sources: https://dev.hume.ai/docs/speech-to-speech-evi/overview , https://www.hume.ai/pricing , https://www.hume.ai/blog/introducing-evi-3