CueLight vs Vogent API

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.

Vogent API

IVR detection and navigation models for outbound calls. No public changelog and no release found since January 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

Vogent API

1. Send an idempotencyKey on POST /dials, a reused key returns 409
2. Create a call with callAgentId, plus toNumber and fromNumberId for phone calls
3. Tell the model when to emit <|transfer|>, since transfers fire on that tag
4. Verify webhooks with the HMAC in X-Elto-Signature
5. Expect new dials to fail at the workspace's concurrent dial limit until calls end