Skip to content
TakoAPI
Back to skills

miranda-sag

by jeffpignataro

Speech & Transcription
357Downloads reported by clawskills.sh
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

ElevenLabs text-to-speech with mac-style say UX.

Description

What This Skill Does

Command-line tool that sends text to ElevenLabs TTS and plays audio locally, mimicking the macOS `say` command interface. Supports multiple ElevenLabs models, voice selection, and expressive audio tags for controlling tone and delivery.

Wraps the ElevenLabs API in a familiar `say`-style CLI so you get high-quality neural TTS without writing any code or opening a browser.

When to Use It

  • Reading long articles aloud while doing other tasks
  • Generating voice lines for demos or prototypes
  • Testing how copy sounds before recording a podcast
  • Quickly auditioning ElevenLabs voices from the terminal
  • Adding spoken notifications to shell scripts

Example Workflow

INPUT

User asks: read this back in a whisper voice

AGENT
  1. 1

    Run sag voices to confirm available voices

  2. 2

    Select a voice and set delivery with [whispers] audio tag

  3. 3

    Run sag -v Roger "[whispers] keep this quiet. [short pause] ok?"

  4. 4

    Audio plays back locally via the sag binary

OUTPUT

Audio of the text spoken in a whispered tone plays through local speakers

Requirements

  • ELEVENLABS_API_KEY environment variable
  • sag CLI installed via Homebrew (steipete/tap/sag)

Installation

clawhub install jeffpignataro/miranda-sag

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links