Voice
Voice is an entrance, not a place. You speak, Milo listens, understands, works and is done — then the pill disappears. It is the same Milo Core the composer talks to, aware of the surface you are on.
The pill
A transient pill at the top centre: ring, state word, live transcript. Nothing else.
- Ring — Milo Vermilion. Its motion is the state: breathing, dashed rotation, pulse, resolve.
- State word — mono microtype. The label carries the state; the ring only echoes it.
- Transcript — live, interface sans, one line, ellipsised. Replaced by Milo's reply in Working and Done.
- Position — fixed, top-centre, 16px from the edge, level 3 shadow. It never covers the primary action.
Five states, then gone
Listening, understanding, working, done, error — each a change of ring and word, then the pill leaves.
Try it
The full sequence runs here; Quick Entry is the keyboard equivalent.
Voice
Runs the full sequence at the top of the viewport, then disappears.
Quick Entry — the keyboard equivalent
Invoke. Type. Submit. Disappear. The toast is Milo's acknowledgement.
Invocation
Hold a key, speak, release; the current surface is the context.
Invocation rules
- 01One entrance from anywhere: the system hotkey, the menu-bar item on macOS, the Hyprland bind on Omarchy, or the ◉ button on a surface.
- 02Milo already knows the context — the current project, task, artifact and machine. You do not name them unless you mean a different one.
- 03Anything that changes files, spends money or touches another machine goes through a PermissionRequest first. Voice never bypasses level 4.
- 04Milo replies in UI language: brief, calm, precise. "On it." "Done." "This needs your approval."
- 05Under reduced motion the ring is still; the state word does all the work.
What voice is not
Not an orb, not a waveform, not a dashboard, not a second assistant.
- A Siri orb
- A giant waveform
- A voice dashboard or history surface
- A separate assistant with a separate memory
- Always listening
Milo speaks with Fable.
James picked it by ear from the film's samples: Kokoro's bm_fable, British English, male, at the film's own pace. "Milo is British."
Fable — British English, male.
- Voice
- Kokoro-82M,
bm_fable, running on the machine (no network) - Pace
- speed 1.331 — the film's sample text in 9.897 s against the film's 9.875 s
- Accent
- spoken with British sounds: 78 of the film's 83 dictionary words match
- Length
- at most two sentences aloud, then "The rest is on screen."
- Interrupt
- SUPER + R stops Milo mid-sentence (measured 287–298 ms)
- Fallback
- Piper, when Kokoro makes no sound — never silence
- The films
- George (
bm_george) narrates; Fable is the system's voice (48.3)
Every voice can be heard and chosen
The picker lists every voice in the Kokoro model — 54, grouped by language: American English 20, British English 8, Spanish 3, French 1, Hindi 4, Italian 2, Japanese 5, Brazilian Portuguese 3, Mandarin Chinese 8 — then five Piper voices as the offline fallback. Each row says its name, sex and id, with Hear it and Use this voice; the one in use says "Milo's voice" instead. Rows are named for a screen reader with their language and sex; all text is at 7:1.
Counted from the full-length capture docs/evidence/voice/settings-voice-all-1280x3900.png in offline-os. British voices run at 1.331; the others at Kokoro's normal 1.0. How it sounds to a person: not yet checked by the source — measured, not heard.
The pill, over real work.
On Omarchy the pill sits at the top centre over whatever is open, says its state in a word, and leaves once read. It never takes the keyboard.
Captured on the laptop, 2026-09-26 (offline-os docs/evidence/screens/2026-09-26-lane-b-loops/). The keys shown are the product's; the brand's pill anatomy is 11.01. REF: https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md