A high-performance CLI for ElevenLabs text-to-speech that brings macOS-style simplicity to professional AI voice generation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install sag
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install sag using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is sag?
sag is a versatile command-line interface designed to bridge the gap between high-quality ElevenLabs text-to-speech models and the intuitive simplicity of the classic macOS 'say' command. It provides developers and AI agents with a streamlined way to generate expressive, human-like audio locally or for integration into automated pipelines. As a key component in the Openclaw Skills collection, sag enables seamless access to advanced models like eleven_v3 for expression and eleven_flash_v2_5 for low-latency requirements.
This skill is particularly valuable for developers who need to add voice capabilities to their agents without managing complex API calls manually. By utilizing sag within the Openclaw Skills framework, users can leverage sophisticated pronunciation rules, normalization settings, and expressive audio tags to produce studio-quality speech from simple text strings.
sag Use Cases
- Generating automated voice responses for AI chat agents using character-specific voices.
- Creating high-fidelity voiceovers for media production via simple CLI commands.
- Implementing audio notifications and alerts in development or server environments.
- Local playback of text content using premium ElevenLabs voices instead of default system voices.
- Testing and prototyping different ElevenLabs models and voice profiles quickly.
How sag Works
- The user or AI agent initiates a command using the sag binary, providing the target text and optional voice parameters.
- The tool authenticates with the ElevenLabs API using a pre-configured ELEVENLABS_API_KEY.
- sag parses the input for special expressive tags like [whispers] or [excited] and applies normalization rules based on the specified language.
- The ElevenLabs engine synthesizes the audio based on the chosen model (v2, v2.5, or v3).
- The generated audio is either streamed for immediate local playback or saved to a specified file path for inclusion in agent responses.
sag Setup
To begin using this skill within the Openclaw Skills ecosystem, install the sag binary via Homebrew:
brew tap steipete/tap
brew install sag
Configure your environment by setting your ElevenLabs API key:
export ELEVENLABS_API_KEY='your_api_key_here'
You can also set a default voice ID to simplify your commands:
export ELEVENLABS_VOICE_ID='your_preferred_voice_id'
sag Data Schema & Taxonomy
| Component | Details |
|---|---|
| Authentication | Uses ELEVENLABS_API_KEY or SAG_API_KEY via environment variables. |
| Models | Supports eleven_v3 (expressive), multilingual_v2 (stable), and flash_v2_5 (fast). |
| Audio Format | Outputs standard high-quality .mp3 files. |
| Expressive Tags | Supports v3 tags: [whispers], [shouts], [sings], [laughs], [sighs], etc. |
| Normalization | Controlled via --normalize flag (auto/off) and --lang for language bias. |
sag Advanced Features
- Support for v3 audio tags to inject human emotions like laughter, sighs, and shouting directly into synthesized speech.
- Advanced normalization settings to handle URLs, units, and numbers correctly across different languages.
- Model-specific prompting optimizations for v2, v2.5, and v3 ElevenLabs engines.
- SSML support for v2 models to provide precise control over break times and pauses.
- Seamless integration with AI agent workflows to output audio files via the MEDIA:/ path syntax.
SKILL.md
Loading
Related Openclaw Skills
qmd
A local search and indexing CLI utilizing BM25 and vector search with MCP support for AI agent integration.
Peekaboo
A comprehensive macOS UI automation CLI designed to capture screens, inspect elements, and drive user inputs for AI agents.
OrderCLI Foodora & Deliveroo Assistant
A command-line interface for tracking active food deliveries, viewing order history, and performing reorders on Foodora and Deliveroo.
Oracle AI Context Bundler
A specialized CLI tool that bundles prompts and source files into a single context-rich request for advanced AI model reviews and debugging.
Slack Actions
A robust integration for managing Slack workspace interactions, including messaging, reactions, and channel organization via AI agents.
Songsee
Songsee is a high-performance CLI utility designed to transform audio files into detailed spectrograms and multi-panel feature visualizations.
Featured*
