          
One voice at a timeSessions queue instead of talking over each other.

AirPods stem controlsClick to pause, skip ahead, or step back.
It waits for youPause it, and new replies queue up quietly.

Just the remoteDrag it anywhere; the full queue lives in the menu bar.

A suggested way to work

Built for this setup. Runs entirely on your Mac — Kokoro voice via MLX, offline and free.

Color-coded tabs , one per project.

Start long runs, then walk away.

Replies announce themselves, one at a time, in order.

Multi-Mac: per-machine voices, no AirPods tug‑of‑war.

iTerm2 › Session › Edit Session › Tab Color

Full Feature List

The queue

One at a time — replies play serially, never over each other
Newest plays next — fresh replies jump ahead of stale backlog
Pause holds everything — new replies wait; a rainbow glow reminds you
Skip one reply — drop the track you don't want without stopping the pipeline
Survives restarts — the queue is restored on launch, silently
Clear played / clear all from the deck footer
Reorder the queue — play now, remove, move up or down per row

Playback

Speed selector — voice rate, in the Settings window or the deck
Volume slider, with every render loudness‑normalized so replies match
Back 10 / forward 10, restart, previous reply, full transport
Mute that keeps queueing — chats build up quietly until you're back
Global quiet hotkey (⌃⌥⌘Space) — silence the room from any app, no permission prompts

The voice

Kokoro neural voice — runs locally on Apple Silicon via MLX, ~54 voices, free
Warm renderer — replies become audio in under a second
Automatic fallback to the best installed macOS voice (Intel works too)
Voice preview in Settings; changing voice re‑renders what's still queued
Per-machine voices — tell your Macs apart by ear

AirPods & media keys

Stem clicks — click to pause, double for next, triple for back
Now Playing — Control Center scrubber while speaking, released when idle so your music keys come back
Two Macs, one pair — decks take turns instead of fighting over your AirPods

What it reads

The whole reply — every part of a long turn, not just the last paragraph
Tuned for the ear — emoji and markdown stripped, paths spoken as filenames, URLs as "link"
Never mid-turn noise — it waits for the settled reply, not tool-call chatter

The app

Floating mini player — auto-appears while speaking, drag it anywhere, Liquid Glass or classic frosted
Menu-bar icon with queue badge and a pulse while playing; Sy mark or speaker glyph
Native Settings window fronting plain dotfiles — shell edits stay in sync
Built-in updates — your version in the menu, an ↑ when a new one is out
Fully local — no accounts, no telemetry, MIT-licensed, works offline

Install

Prompt

Install SpeakySpeak on this Mac: clone https://github.com/radam5000/speakyspeak and follow INSTALL.md step by step, verifying each step.

Requires macOS 14 or newer, Claude Code, Homebrew, and the Xcode command-line tools.

INSTALL.md · github.com/radam5000/speakyspeak

Not exactly your setup? The instructions are written for Claude to adapt — desktop app, VS Code, Cursor, a different voice, two Macs. Just ask it.