gpt-realtime-mini

`gpt-realtime-mini` is OpenAI's cost-efficient realtime speech-to-speech model — the same unified audio-in/audio-out product pattern as `gpt-realtime`, tuned for ~3× lower cost. On CallMissed, select it as `llm_model=gpt-realtime-mini` when creating a voice session.

Text: $0.60 in / $2.40 out per 1M; audio: $10 in / $20 out per 1M. On CallMissed it bills against active call minutes — roughly $0.118/min — so you don't have to do token math. Best for consumer-facing assistants, internal help lines, and high-volume pilots where full realtime quality is overkill.

Voices: alloy, echo, shimmer, ash, ballad, coral, sage, verse, marin, cedar.