CueLight vs Hume EVI (Empathic Voice Interface)

CueLight

CueLight gives a voice pipeline a local end-of-turn probability every 20 ms from audio alone, with a 1.9 MB model and Apache-2.0 weights. It is one day old, English only, installs from Git rather than PyPI, has no CI or changelog, and its accuracy figures are the author's own.

Hume EVI (Empathic Voice Interface)

Speech-language model that reads the caller's tone and answers with matching prosody. One account-wide key, sent in the WebSocket and Twilio webhook URLs. Hume ends API access on 13 November 2026.

CueLight

1. Feed 320 float32 samples at 16 kHz mono per push. Resample first, or the call raises an AssertionError
2. Spell the preset as snappy or careful. Any other name silently uses default thresholds
3. Call clear() before a new call or session. Pass reset_on_turn_start=False if your pipeline already resets per turn
4. Pin weights by downloading them to a local folder and passing that path to from_pretrained
5. Don't use it to identify speakers or clone voices. The training data's conditions forbid it

Hume EVI (Empathic Voice Interface)

1. Create a config with a voice first, EVI 3 has no default
2. Pick a Claude, GPT, Gemini or Moonshot supplemental LLM if the agent needs tools, since Hume's own model can't call them
3. Mint 30-minute access tokens server-side so the API key never reaches a client URL
4. Turn on 'Do not retain data' and 'Do not use for training' at app.hume.ai before sensitive calls
5. Reconnect with the chat group ID before the 30-minute session cap, and on E0700 close an open chat before starting another