Generates ElevenLabs text-to-speech audio with local playback via the sag CLI.
npx skills add https://github.com/AmirulAndalib/Vilvona-AI --skill sag-amirulandalib
Please help me install this Agent Skill. Skill: sag Source: https://github.com/AmirulAndalib/Vilvona-AI/tree/main/skills/sag Command: npx skills add https://github.com/AmirulAndalib/Vilvona-AI --skill sag-amirulandalib
sag "Hello there" to synthesize speech with ElevenLabs models like eleven_v3, eleven_multilingual_v2, or eleven_flash_v2_5 and play it locally. - Voice and Delivery Control: Select voices with -v, set defaults via ELEVENLABS_VOICE_ID, and use v3 audio tags like [whispers], [excited], or [short pause] for expressive delivery. - Voice Chat Replies: Generate character-voiced audio responses (e.g., a crazy scientist voice) and attach them to chat replies as media files. - Use Case: A user asks the assistant to explain a concept in a dramatic voice; the assistant runs sag -v Clawd -o /tmp/voice-reply.mp3 "..." and sends the audio file back. ## Quick Start Ask the assistant to say a message out loud using sag, optionally specifying a voice or style such as "say hello in a whispering voice".High-intent search queries and answers about installing and using this skill.
Install the sag CLI via Homebrew, set your ELEVENLABS_API_KEY, then run `sag "Your text here"` to synthesize and play speech locally. Use `sag -o output.mp3 "text"` to save audio to a file instead.
List available voices with `sag voices`, then pass one with the `-v` flag, such as `sag -v "Roger" "Hello"`. You can also set a default voice using the ELEVENLABS_VOICE_ID or SAG_VOICE_ID environment variable.
The default eleven_v3 model is the most expressive and supports audio tags like [whispers] and [excited]. Use eleven_multilingual_v2 for stable output or eleven_flash_v2_5 when speed matters more than expressiveness.
No, eleven_v3 does not support SSML `<break>` tags; use bracket tags like [pause], [short pause], or [long pause] instead. The v2 and v2.5 models do support SSML `<break time="1.5s" />` syntax.
Respell the word phonetically, add hyphens, or adjust casing as a first fix. For numbers, units, and URLs, use `--normalize auto`, and use `--lang` to bias normalization toward a specific language.
trpc-groupGenerates ElevenLabs text-to-speech audio with mac-style say command UX.
ViewWayGenerate MP3 speech from text using Hume AI or OpenAI.
brikkoAIGenerate natural-sounding speech audio via the ElevenLabs API.
balic-AI-ML-R-D-ResourcesConvert text to speech with ElevenLabs TTS and local playback.