Setup & Installation
openclaw skills install @jeffpignataro/miranda-sag
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install miranda-sag
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
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: read this back in a whisper voice
AGENT
- 1Run `sag voices` to confirm available voices
- 2Select a voice and set delivery with `[whispers]` audio tag
- 3Run `sag -v Roger "[whispers] keep this quiet. [short pause] ok?"`
- 4Audio plays back locally via the `sag` binary
OUTPUT
Audio of the text spoken in a whispered tone plays through local speakers
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.
ELEVENLABS_API_KEY environment variablesag CLI installed via Homebrew (steipete/tap/sag)