As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/hume-evi/

# Hume EVI 3 / EVI 4 mini (speech-to-speech)

Hume AI, EVI family. Status: current. Type: speech and audio. Released: 2025-05-29.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hume API (EVI WebSocket) | `EVI version 3 or 4-mini (set in EVI config)` | wss://api.hume.ai/v0/evi/chat | https://dev.hume.ai/docs/speech-to-speech-evi/overview |
| Web app |  |  | https://platform.hume.ai |

## Pricing

- Per minute: $0.06
- Unit as published: per minute overage on Free/Pro ($0.07 Starter/Creator, $0.05 Scale, $0.04 Business); plans include monthly minutes
- Source: https://www.hume.ai/pricing
- Last checked: 2026-09-29

## Specs

- Input: audio, text
- Output: audio, text
- Context window: not published
- Max output: not published
- Open weights: no
- Licence: proprietary

## Where it stands

- Newer speech and audio models in the registry since its release: 93. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- After it from Hume AI: Hume Octave 2 (TTS) (2025-10-01) https://postcutoff.com/m/hume-octave-2/
- Closed weights; access is hosted only.

## What stands out

- 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: https://www.hume.ai/blog/introducing-evi-3
- 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: https://www.hume.ai/blog/octave-2-launch

## Notes

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.

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

Model page: https://postcutoff.com/m/hume-evi/