Generates ElevenLabs text-to-speech audio with local playback via the sag CLI.
npx skills add https://github.com/travis-burmaster/agentbox --skill sag-travis-burmaster
Please help me install this Agent Skill. Skill: sag Source: https://github.com/travis-burmaster/agentbox/tree/main/agentfork/skills/sag Command: npx skills add https://github.com/travis-burmaster/agentbox --skill sag-travis-burmaster
sag -v Clawd -o /tmp/voice-reply.mp3 "..." and attach it to the chat response. ## Quick Start Ask the assistant to say a short message out loud using sag, for example by requesting a spoken greeting in a specific voice.High-intent search queries and answers about installing and using this skill.
Install the sag CLI via Homebrew (brew install steipete/tap/sag), set your ELEVENLABS_API_KEY, then run sag "Your text here" to generate and play speech locally. Use -o to save output as an MP3 file.
List available voices with sag voices, then select one using the -v flag (e.g., sag -v "Roger" "Hello"). You can also set a default voice with the ELEVENLABS_VOICE_ID or SAG_VOICE_ID environment variables.
Use eleven_v3 (the default) for expressive delivery with audio tags, eleven_multilingual_v2 for stable multilingual output, or eleven_flash_v2_5 when speed matters. Note that v3 does not support SSML break tags.
SSML support depends on the model: eleven_v3 does not support <break> and instead uses tags like [pause] or [short pause]. Models v2 and v2.5 support <break time="1.5s" />, but <phoneme> is not exposed in sag.
Fix pronunciation by respelling words, adding hyphens, or adjusting casing. For numbers, units, and URLs, use --normalize auto, and add --lang en|de|fr to guide normalization for a specific language.
trpc-groupGenerates ElevenLabs text-to-speech audio with mac-style say command UX.
buda-aiExtract and enhance audio from video files for MP3/WAV/AAC output.
Moshe-shipConvert Arabic audio to text and generate spoken responses using Whisper and TTS.
hasnaGenerate MP3 audio from text using ElevenLabs, OpenAI TTS, or Google Text-to-Speech.