Speech & vision
STT/TTS adapters. Currently placeholders — a scaffold, not a shipped feature.
Planned
Placeholder only
Speech and vision adapters return placeholders. There is no real STT/TTS or vision pipeline behind them yet. This page documents the intended shape, not a working feature.
The intent is for STT/TTS and vision to be processed locally on hardware you own. Until the matrix marks them otherwise, treat these adapters as scaffolds.
Speech & vision (STT/TTS)Mock
Was this page helpful?
Last updated June 3, 2026