A voice schema defines an AI model's writing style. It uses specific axes to describe how the AI model should write. Each axis requires a clear, single choice.
By Pawan Nayar · from the LLOS AI Learning record
A voice schema defines an AI model's writing style.
It uses specific axes to describe how the AI model should write. Each axis requires a clear, single choice.
A 14-axis voice schema replaces general descriptions of writing style. It breaks down voice into distinct parts. Each part, or axis, needs a precise choice. This stops vague language like 'elegant' or 'balanced'. The schema includes axes like 'Primary Mark', 'Rhythm', 'Skip', and 'Fav Word'. It also covers 'Sentence DNA', 'Punct Goal', 'Theme', and 'Hidden Mood'. Other axes are 'Texture', 'Space', 'Vocabulary', 'Final Beat', and 'Persona'. Developers can use reference voices to understand each axis. These are examples of famous writers' styles. A 'YOUR STANDING' block shows the AI model's current style choices. This helps a developer see how the AI model's voice is built.
A developer wants an AI model to write like a specific historical figure. The developer uses the voice schema. For the 'Fav Word' axis, the developer chooses 'indeed'. For 'Sentence DNA', the developer chooses 'short and direct'. This ensures the AI model's output matches the desired style, avoiding general descriptions.
Resolved from this lesson's own record — real definitions, not invented for this page.
More from the same record, pulled by shared topic — not written new for this page.
An AI model can have hundreds of voices. These voices are grouped into categories.
An AI model's 'voice' setting defines how sentences are built. It also defines the special ways sentences change or turn.
A three-hop semantic divergence engine is a tool for expanding text. It takes a short idea and generates many related but different ideas.
An AI model must use plain English in Grammar Academy JSON fields. The only allowed formatting is italics.
A voice schema defines an AI model's writing style. It uses specific axes to describe how the AI model should write. Each axis requires a clear, single choice.