Skill

Pass

Audit score 90

sag

steipete/clawdis

ElevenLabs text-to-speech with native macOS say-like command interface.

What is sag?

sag is a command-line tool that brings ElevenLabs TTS to your terminal with a familiar macOS say-style UX. Use it to generate and play back expressive speech with support for multiple voices, models, and SSML-like audio tags.

Generate and play audio locally using ElevenLabs API
Support three TTS models: v3 (expressive), multilingual v2, and fast v2.5
Apply audio tags like [whispers], [shouts], [sings], [excited], [crying] for delivery control
Normalize pronunciation with respelling, hyphens, language bias, and auto-normalization options
List available voices and access model-specific prompting tips
Output audio files for integration into chat responses

How to install sag

npx skills add https://github.com/steipete/clawdis --skill sag

Prerequisites

ElevenLabs API key (set as ELEVENLABS_API_KEY or SAG_API_KEY environment variable)
sag binary installed (via brew: steipete/tap/sag)

Claude Code

Cursor

Windsurf

Cline

How to use sag

1.Set your ElevenLabs API key: export ELEVENLABS_API_KEY=your_key
2.Run sag "text" to generate and play audio immediately
3.List available voices with sag voices to choose a voice ID
4.Use sag -v VoiceID "text" to speak with a specific voice
5.Add audio tags like [whispers], [excited], [short pause] within your text for delivery control
6.For output files, use sag -o /path/to/file.mp3 "text" and include via MEDIA:/path/to/file.mp3 in responses
7.Check sag prompting for model-specific tips on the v3, v2, or v2.5 models

Use cases

Good for

Generate voice replies in chat interfaces with character-specific delivery (scientist, calm, dramatic)
Read long-form text aloud with expressive inflection using audio tags
Normalize technical terms, URLs, and numbers for clear pronunciation
Create audio files for downstream processing or media inclusion
Experiment with different voices and models before committing to long outputs

Who it's for

Developers building voice-enabled chat agents or applications
Content creators needing expressive text-to-speech output
Users who prefer command-line tools over web interfaces
Teams using ElevenLabs API and wanting local playback

sag FAQ

Which model should I use?

Default is eleven_v3 (most expressive). Use eleven_multilingual_v2 for stable multilingual support, or eleven_flash_v2_5 for speed.

How do I fix mispronounced words?

Respell the word (e.g., 'key-note' for keynote), add hyphens, adjust casing, or use --normalize auto for numbers/units/URLs.

What audio tags does v3 support?

v3 supports [whispers], [shouts], [sings], [laughs], [sighs], [sarcastic], [excited], [crying], and others. Use [pause], [short pause], [long pause] for timing (not SSML <break>).

Can I set a default voice?

Yes, set ELEVENLABS_VOICE_ID or SAG_VOICE_ID environment variable, or use -v VoiceID on the command line.

How do I include audio in a chat response?

Generate audio with sag -o /tmp/file.mp3 "text", then include MEDIA:/tmp/file.mp3 in your response.

Full instructions (SKILL.md)

Source of truth, from steipete/clawdis.

name: sag description: "ElevenLabs text-to-speech with mac-style say UX." homepage: https://sag.sh metadata: { "openclaw": { "emoji": "🔊", "requires": { "bins": ["sag"], "env": ["ELEVENLABS_API_KEY"] }, "primaryEnv": "ELEVENLABS_API_KEY", "install": [ { "id": "brew", "kind": "brew", "formula": "steipete/tap/sag", "bins": ["sag"], "label": "Install sag (brew)", }, ], }, }

sag

Use sag for ElevenLabs TTS with local playback.

API key (required)

ELEVENLABS_API_KEY (preferred)
SAG_API_KEY also supported by the CLI

Quick start

sag "Hello there"
sag speak -v "Roger" "Hello"
sag voices
sag prompting (model-specific tips)

Model notes

Default: eleven_v3 (expressive)
Stable: eleven_multilingual_v2
Fast: eleven_flash_v2_5

Pronunciation + delivery rules

First fix: respell (e.g. "key-note"), add hyphens, adjust casing.
Numbers/units/URLs: --normalize auto (or off if it harms names).
Language bias: --lang en|de|fr|... to guide normalization.
v3: SSML <break> not supported; use [pause], [short pause], [long pause].
v2/v2.5: SSML <break time="1.5s" /> supported; <phoneme> not exposed in sag.

v3 audio tags (put at the entrance of a line)

[whispers], [shouts], [sings]
[laughs], [starts laughing], [sighs], [exhales]
[sarcastic], [curious], [excited], [crying], [mischievously]
Example: sag "[whispers] keep this quiet. [short pause] ok?"

Voice defaults

ELEVENLABS_VOICE_ID or SAG_VOICE_ID

Confirm voice + speaker before long output.

Chat voice responses

When the user asks for a "voice" reply (e.g., "crazy scientist voice", "explain in voice"), generate audio and send it:

# Generate audio file
sag -v Clawd -o /tmp/voice-reply.mp3 "Your message here"

# Then include in reply:
# MEDIA:/tmp/voice-reply.mp3

Voice character tips:

Crazy scientist: Use [excited] tags, dramatic pauses [short pause], vary intensity
Calm: Use [whispers] or slower pacing
Dramatic: Use [sings] or [shouts] sparingly

Default voice for Clawd: lj2rcrvANS3gaWWnczSX (or just -v Clawd)

Related skills

More from steipete/clawdis and the wider catalog.

session-logs

steipete/clawdis

Search and analyze your conversation history using jq and ripgrep.

2.6k installs

sherpa-onnx-tts

steipete/clawdis

Offline text-to-speech using sherpa-onnx—no cloud, runs locally on macOS, Linux, and Windows.

2.4k installsAudited

skill-creator

steipete/clawdis

Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.

2.3k installsAudited

slack

steipete/clawdis

Send, read, edit, delete, and react to Slack messages with full channel and member management.

2.2k installs

songsee

steipete/clawdis

Generate spectrograms and multi-panel audio visualizations from MP3, WAV, and other formats.

2.3k installs

sonoscli

steipete/clawdis

Control Sonos speakers on your local network—discover, play, pause, adjust volume, and group speakers.

2.5k installs