-
Notifications
You must be signed in to change notification settings - Fork 32
Add scoped QR-hosted FableLoom sessions with half-duplex protagonist voice #5383
Copy link
Copy link
Closed
Labels
architectureArchitecture and SOLIDArchitecture and SOLIDarea:privacyPII vault, trusted-org registry, data-broker opt-outPII vault, trusted-org registry, data-broker opt-outarea:story-builderStory Builder featureStory Builder featurearea:voiceVoice stack: STT/TTS pipeline, proactive speech, voice tools, call bridgeVoice stack: STT/TTS pipeline, proactive speech, voice tools, call bridgeeffort:maxDispatch reasoning effort: maximumDispatch reasoning effort: maximummodel:heavyDispatch capability: heavyDispatch capability: heavyplanTracked by /do:replanTracked by /do:replanplan-featureFeature plan filed by the plan-feature brainstormFeature plan filed by the plan-feature brainstorm
Description
Activity
Metadata
Metadata
Assignees
Labels
architectureArchitecture and SOLIDArchitecture and SOLIDarea:privacyPII vault, trusted-org registry, data-broker opt-outPII vault, trusted-org registry, data-broker opt-outarea:story-builderStory Builder featureStory Builder featurearea:voiceVoice stack: STT/TTS pipeline, proactive speech, voice tools, call bridgeVoice stack: STT/TTS pipeline, proactive speech, voice tools, call bridgeeffort:maxDispatch reasoning effort: maximumDispatch reasoning effort: maximummodel:heavyDispatch capability: heavyDispatch capability: heavyplanTracked by /do:replanTracked by /do:replanplan-featureFeature plan filed by the plan-feature brainstormFeature plan filed by the plan-feature brainstorm
Part of #5377. Blocked by #5382 and #5380. #5381 is an optional enhancement, not a blocker.
Goal
Add same-tailnet/same-LAN two-device hosted play: the computer runs authored pre-rendered video, a phone joins by QR code as the microphone/audience UI, and the off-screen protagonist answers in the approved character voice with no overlapping speech.
Proposed approach
LISTENING -> THINKING -> SPEAKING -> LISTENING, no barge-in, measured echo tail, one configured TTS output target, and runtime revalidation of the live-conversation gate.Acceptance criteria
LISTENING; rendered character dialogue and live character TTS never overlap viewer input.Out of scope