LiveKit on X: "@SpaceXAI @grok Expressive mode is on, so @SpaceXAI's TTS handles pacing and delivery inline without prompt changes. Rigel for clinical, Celeste when the caller needs reassurance.
Full recipe: https://t.co/tIgnOMMP9L"
Expressive mode is on, so @SpaceXAI's TTS handles pacing and delivery inline without prompt changes. Rigel for clinical, Celeste when the caller needs reassurance.
Full recipe:
We built a patient intake agent with @SpaceXAI that runs end to end on Grok voice models.
Grok STT → Grok 4.3 → Grok TTS, cascaded through LiveKit Inference. Three model strings in one AgentSession. No separate API key, no separate billing, ZDR on every hop.
Talk to it:
This is the first fully cascaded voice demo on @grok.
Patient intake flows require a fully cascaded pipeline: a real transcript, tool calls against the chart, and control over every turn. It books, reschedules, and triages red-flag symptoms to emergency care.
Expressive mode is on, so @SpaceXAI's TTS handles pacing and delivery inline without prompt changes. Rigel for clinical, Celeste when the caller needs reassurance.
Full recipe: