CueLight vs Vapi 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.

Vapi API + MCP

Voice agents can combine supported transcription, model and voice providers, including customer-supplied endpoints. Per-minute cost depends on the selected providers.

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

Vapi API + MCP

1. Read subscriptionLimits.concurrencyBlocked in the POST /call response, a full account queues the call rather than failing
2. Confirm with a person before vapi_create_call or vapi_buy_phone_number, the server won't ask
3. Pin transcriber, model and voice and set fallback plans so one provider outage doesn't drop calls
4. Read the call log's cost breakdown to see what each provider charged
5. Check @vapi-ai/server-sdk isn't pinned to 0.11.1, 0.11.2, 1.2.1 or 1.2.2