Readout

    1

    Speak terminal and agent output aloud on macOS. Voice and speed follow the text's tone (success, error, calm). Local TTS, optional Haiku tone detection.

    $3

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Readout

    Example session with this skill installed

    readout --dry-run "build passed, all 214 tests green"

    • Read your context and instructions
    • Compiled the readout

    tone=success voice=Moira rate=190 chars=35

    Connects securely to your tools. The creator never sees your data.

    About this skill

    CLI that speaks text aloud using local macOS TTS (say). Tone picks the voice:

    tonevoiceratewhen
    neutralSamantha175default, code, status
    successMoira190positive keywords
    errorDaniel165failure keywords
    calmKaren150long blocks (>600 chars)

    Tone priority: --tone flag, then Haiku 4.5 (only if ANTHROPIC_API_KEY is set), then a local word-list heuristic. The Haiku call sends up to 2000 chars of the text to the Anthropic API; tell the user this before enabling it. With no key, nothing leaves the machine.

    Requires macOS and Python 3.9+. Whisper is speech-to-text, not text-to-speech; this tool uses say, edge-tts, or piper.

    macOS only. Last-output capture stores the previous command line, not its output; pipe explicitly (cmd | readout) for reliable capture. The piper backend flags are not compatible with the piper CLI yet, so use say or edge. Audio is not tested in headless or CI shells.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 18 days ago

    Requires

    macOS
    Python 3.9+
    zsh
    Python

    Permissions

    Allowed Hosts

    api.anthropic.com (only when ANTHROPIC_API_KEY is set)

    File Scopes

    ~/.cache/readout/
    (read/write)
    ~/.claude/skills/readout/readout.py
    (install
    location)
    ~/.zshrc
    (user
    appends
    hook
    manually)

    Sends up to 2000 characters of the text to the Anthropic API for tone classification only when ANTHROPIC_API_KEY is set. Without a key everything stays local. Never edits ~/.zshrc itself.

    Listed18 days ago

    What's inside

    Frequently Asked Questions

    Speak terminal and agent output aloud on macOS. Voice and speed follow the text's tone (success, error, calm). Local TTS, optional Haiku tone detection.

    This skill uses the open SKILL.md standard. Use it through an MCP-compatible agent connected to Agensi, and check the compatibility information on this page for confirmed agents and required capabilities.

    Connect your AI agent to Agensi through MCP, then ask it to use Readout on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.

    New in Productivity