AI Voice Assistant
voice-assistant
A voice-first conversation — live waveform states, a recording input, a spoken transcript and a typed fallback.
More from @scrimui
How much of the context window is gone and to what — system prompt, files, history — plus what gets dropped first when the next message does not fit.
The passages retrieval actually returned, with similarity scores and a visible relevance floor — including the case where nothing cleared it.
Live spend per message and per conversation — cached input priced apart from fresh, reasoning tokens shown without double-counting, and a visible ~ when a provider did not report enough to be sure.
Render an AI reply token by token like ChatGPT's typing effect — blinking cursor, stop button, and no layout jump as the text grows.
What to show when a generation fails — a plain-English reason, a retry button, and a countdown for rate limits.
The loading state before the first token — bouncing dots, a blinking caret, or a labeled status line while the model thinks.
Upload a document, watch fields fill in, then review the flagged ones — per-field confidence, corrections that keep the original, export earned.
Switches for the tools a model may use — web search, code execution, file access — with unmistakable on and off states.