speech-models
band: coolmomentum: stable
score: 0.004
Episodes (4)
Trajectory notes
- 2026-09-11T01:28:34Z: tavus-sparrow-2-conversational-flow closed (faded) — Tavus’s dedicated listen/wait/speak controller converges with the interaction-management side of Scott’s Cognitive Pipelining and The Fast Slow Split, offering a candidate to evaluate for turn-taking in his Twilio voice lab a
- 2026-08-30T16:30:43Z: gemini-35-transcribe-release closed (window-closed) — Google’s Gemini-native transcription offering converges with Scott’s existing practice of treating speech recognition as a swappable, task-routed component, and it is directly testable in his ambient-conversation and local s