<%= model.label %>
<%= model.recommended ? 'Recommended starting point' : 'Fallback option' %> · <%= Math.round(model.bytes / 1048576) %> MiB
Experimental companion
-Server-hosted speech recognition for selected OBS sources. Live Twitch delivery remains blocked until the native OBS caption compatibility test passes on the target setup.
-First usable path
Lumi host
Lumi AI may already occupy most GPU memory. The MVP warns and benchmarks; it does not unload Lumi AI models automatically.
-Access
No companion is paired yet.
<% } %> -<%= device.id %>The native OBS 31+ caption path still needs target-machine validation. Lumi will not present a local simulated caption as live Twitch success.
+Curated choices
<%= model.recommended ? 'Recommended starting point' : 'Fallback option' %> · <%= Math.round(model.bytes / 1048576) %> MiB
Complete one clear step at a time. Existing server administration remains in Lumi; streaming-computer controls remain in Companion.
Speech recognition runs on the Lumi server, never on the streaming computer.
Privacy: raw audio is held only in bounded memory and is never written to disk by default. Diagnostic caption text is retained for seven days unless disabled.
+Lumi warns and benchmarks when Lumi AI already occupies GPU memory. It never unloads AI models automatically.
Credentials are revocable and scoped to Companion capabilities.
Use Download Companion to create a package that expires after 15 minutes and works once.
Downloads require confirmation and checksum verification before a model can load.
<%= model.recommended ? 'Recommended starting point' : 'Fallback option' %> · <%= Math.round(model.bytes / 1048576) %> MiB
Raw audio is held only in bounded memory and is never written to disk by default. Diagnostic caption text is retained for seven days unless disabled.
<%= section.description %>
No Companion issues are currently reported.