CueLight vs Retell AI API + MCP

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.

Retell AI API + MCP

Published per-minute price for every component, from $0.07 a minute all in. Call data kept indefinitely unless retention is set per agent.

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

Retell AI API + MCP

1. Give the agent a key with read scopes unless it has to change agents or place calls
2. Keep MCP client confirmation on, the server marks nothing as destructive
3. Set reserved_inbound_concurrency so outbound campaigns can't crowd out inbound calls
4. Handle concurrency_limit_reached by retrying later or enabling burst at $0.10 a minute extra
5. Set a data retention period on each agent that handles personal data