CueLight vs Deepgram Voice Agent 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.

Deepgram Voice Agent API

$0.075 a minute all in on Standard, $0.050 with your own LLM and TTS, $200 of credit with no card. No phone numbers or SIP, so you bridge Twilio or another carrier yourself.

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

Deepgram Voice Agent API

1. Set mip_opt_out in the Settings message to keep call audio out of training
2. Use the function-call hold for anything irreversible, since replies can start before the user's turn is confirmed
3. Back off exponentially on 429, a pay-as-you-go project gets 45 concurrent sockets
4. Pin the LLM version, an unpinned Gemini route failed for 1.5 hours on 21 July 2026
5. Mint browser tokens with ttl_seconds, not ttl, or they expire after 30 seconds