Unofficial hosted planner

Turn FluidVoice into a private Mac dictation workflow you can trust every day.

Map voice engines, permissions, hotkeys, command mode, write mode, audio history, and local-first AI boundaries before you rely on dictation across your Mac.

View pricing plans Open planner preview Source notes

Unofficial boundary GPL-3.0 source v1.6.1 release noted

Mac dictation workflow planner with waveform, model cards, and privacy boundary panels.

Usable preview

Voice workflow preview

Primary role Weekly dictation minutes Languages Mac hardware Command Mode History

{
  "status": "ready_for_input",
  "output": "Enter workflow assumptions to preview FluidVoice setup risks."
}

Full export is gated behind pricing and paid access.

Product thesis

Dictation is faster when the setup is already decided.

FluidVoice brings together local-first speech, model choice, Mac permissions, overlays, Write Mode, Command Mode, local history, and optional enhancement. The planner turns those choices into a launch checklist instead of a settings maze.

Choose models

Compare zero-download, low-latency, multilingual, Intel-compatible, and high-accuracy paths.

Set permissions

Prepare microphone, accessibility, Apple Events, speech recognition, startup, and hotkey guidance.

Protect output

Decide when cloud providers, history, analytics, exports, and local enhancement are acceptable.

Gate exports

Preview the plan freely; full exports and policy packs route through pricing before API access.

Trust data ledger

Real source facts, clearly separated from sample output.

4,781GitHub stars collected July 1, 2026

296GitHub forks from the upstream repo

10,231Latest release asset downloads observed

GPL-3.0Code license with local AI runtime boundary noted

This site uses source facts from the upstream project and deterministic sample planner output. It does not claim maintainer endorsement, user counts, revenue, or official download status for this planner.

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.

Popular workflows

Pick the page that matches the decision in front of you.

Model selection plan

Choose Apple Speech, Nemotron, Parakeet, Cohere, or Whisper based on work style.

Command Mode guardrails

Separate safe voice actions from confirmation-required automation.

Write Mode prompts

Plan dictation and rewriting behavior across apps and text fields.

Local-first checklist

Document cloud opt-in, analytics, history, and export boundaries.

macOS permissions

Prepare microphone, accessibility, Apple Events, and speech recognition onboarding.

Fluid Intelligence notes

Plan local enhancement without confusing it with the GPL app boundary.

Related AI workflow reference

Readers comparing workflow assumptions can also review MiroFish AI Simulator, a companion reference for simulation-style product reasoning.

For creative and design workflows that rely on long briefs, the Kimi K3 resource hub is a useful companion for model planning notes. See Kimi K3 resource hub.