README / app /data /faq.json
CJGibs's picture
Build Aether Voice Studio Docker Space
703a33a
[
{
"question": "Why multiple MOSS routes?",
"answer": "Each route maps to a distinct workflow class. That keeps latency, output structure, and UI assumptions explicit instead of burying everything behind a single generic voice endpoint."
},
{
"question": "Why separate TTS Live from Studio?",
"answer": "Immediate prompt iteration and long-form production behave differently. TTS Live optimizes for speed, while Studio supports cloning, dialogue composition, and export-oriented workflows."
},
{
"question": "What is voice design?",
"answer": "Voice design is the creation of reusable synthetic voice assets with controlled style, persona, and later operational metadata."
},
{
"question": "What is a voice registry?",
"answer": "A voice registry is a machine-readable inventory of available voice assets, their provenance, allowed routes, and usage semantics."
},
{
"question": "What is the role of Chatterbox?",
"answer": "Chatterbox is the fallback path. It provides compatibility and resilience when a primary route is unavailable or inappropriate for the requested workflow."
},
{
"question": "Is Sound Design included?",
"answer": "The lane is designed into the information architecture now, but it remains a planned surface in v1 rather than a fully interactive production subsystem."
}
]