skills.rest
JEROME-PRAKASH-L
JEROME-PRAKASH-LCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

sag

Generates ElevenLabs text-to-speech audio with local playback via the sag CLI.

1|Updated Jun 9, 2026
Search Tags:#cli#text-to-speech#audio#elevenlabs#tts#voice generation#sag
One-click install
npx skills add https://github.com/JEROME-PRAKASH-L/openclaw --skill sag-jerome-prakash-l
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/JEROME-PRAKASH-L/openclaw/tree/main/skills/sag
Command: npx skills add https://github.com/JEROME-PRAKASH-L/openclaw --skill sag-jerome-prakash-l

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Converting text into natural-sounding spoken audio requires an API key, model selection, voice configuration, and pronunciation tuning, which is tedious to handle manually for every message or voice reply. ## Core Features & Use Cases - Text-to-Speech Generation: Run sag commands to synthesize speech with ElevenLabs models like eleven_v3, eleven_multilingual_v2, or eleven_flash_v2_5. - Voice and Delivery Control: Select voices, apply v3 audio tags such as [whispers] or [excited], and tune pronunciation with respelling, normalization, and language hints. - Use Case: When a user asks for a "crazy scientist voice" reply in chat, generate an MP3 with a chosen voice and expressive tags, then attach the audio file to the response. ## Quick Start Ask the assistant to say "Hello there" out loud using the sag text-to-speech tool with your configured ElevenLabs API key.

Frequently Asked Questions about sag

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert text to speech with ElevenLabs from the command line?▼

Install the sag CLI via Homebrew and run sag followed by your text in quotes, for example sag "Hello there". Set the ELEVENLABS_API_KEY environment variable first, and optionally pick a voice with the -v flag.

Which ElevenLabs model should I use for text-to-speech?▼

Use eleven_v3 for expressive delivery with audio tags, eleven_multilingual_v2 for stable output, or eleven_flash_v2_5 for the fastest generation. The default in sag is eleven_v3.

Does ElevenLabs v3 support SSML break tags?▼

No, eleven_v3 does not support SSML <break> tags. Use bracket tags like [pause], [short pause], or [long pause] instead. SSML <break time="1.5s" /> works only with v2 and v2.5 models.

How do I fix mispronounced words in text-to-speech output?▼

Respell the word phonetically, add hyphens, or adjust casing as a first fix. For numbers, units, and URLs, use the --normalize auto flag, and set --lang to guide normalization for a specific language.

What do I need to install before using sag for speech synthesis?▼

You need the sag binary, installable via brew install steipete/tap/sag, plus an ElevenLabs API key set as ELEVENLABS_API_KEY or SAG_API_KEY. A default voice can be set with ELEVENLABS_VOICE_ID.

Related Skills

Explore More Content & Communication Skills→
trpc-grouptrpc-group
1.8k

sag

Generates ElevenLabs text-to-speech audio with mac-style say command UX.

Official
Basic
dgethingsdgethings

webex-voice-interface

Transcribe WebEx voice clips and generate text replies with optional MP3 audio.

Community
Intermediate
Pixazo-AIPixazo-AI

gemini-voice

Generates speech from text and transcribes audio via the Gemini Voice API on Pixazo.

Official
Intermediate
hasnahasna
24

Audio Generation

Generate MP3 audio from text using ElevenLabs, OpenAI TTS, or Google Text-to-Speech.

Official
Intermediate