What README says
Fluid Intelligence is described as a separate privately maintained local AI runtime for smart formatting, capitalization, and post-processing.
fluid intelligence local ai
Use local enhancement as a policy choice, not a mystery switch.
Use the planner to translate FluidVoice source facts into a concrete setup, privacy, model, and workflow decision.
Unofficial boundary
GPL-3.0 source
v1.6.1 release noted
Workflow
What this page helps decide.
What to plan
Disk space, download expectations, who can enable it, whether local-only is required, and how users should validate output quality.
Boundary
The core FluidVoice app is GPL-3.0, while the Fluid Intelligence runtime is described separately in the README. Source notes keep that distinction visible.
Decision matrix
What the planner checks before daily use.
| Area | Question | Planner output |
|---|---|---|
| Voice engine | Does the work need zero-download setup, low latency, multilingual support, Intel compatibility, or high accuracy? | Model recommendation with setup notes and disk expectations. |
| Permissions | Can users explain microphone, accessibility, Apple Events, and speech recognition access before approving prompts? | Onboarding checklist and risk labels. |
| Mode policy | Where should Command Mode, Write Mode, per-app prompts, and direct insertion be allowed? | Mode map with safe, review, and blocked zones. |
| Privacy | Which opt-ins are allowed: cloud enhancement, Fluid Intelligence, analytics, beta builds, local history, and exports? | Privacy boundary and data-retention notes. |