Generate local ElevenLabs text-to-speech audio from user prompts.
npx skills add https://github.com/JOHNNYWHITEMIKE/openclaw --skill sag-johnnywhitemike
Please help me install this Agent Skill. Skill: sag Source: https://github.com/JOHNNYWHITEMIKE/openclaw/tree/main/openclaw/.openclaw/openclaw/skills/sag Command: npx skills add https://github.com/JOHNNYWHITEMIKE/openclaw --skill sag-johnnywhitemike
Sag converts your written text into natural-sounding audio so you can produce voice messages, spoken explanations, and audio replies without manually setting up a TTS workflow.
Generate speech from the text "Hello there" by running: sag "Hello there".
High-intent search queries and answers about installing and using this skill.
To generate ElevenLabs text-to-speech audio, you can use a command-line tool that accepts your text prompt and plays the synthesized speech locally. You simply input your text and the tool handles the voice synthesis and audio playback.
Yes, you need an API key to generate text-to-speech voice output. The process requires an ELEVENLABS_API_KEY or a SAG_API_KEY configured in your environment to authenticate requests and produce the audio playback.
Yes, you can control pronunciation and pacing in voice synthesis by applying normalization rules, language bias, and SSML-like delivery tags. These features allow you to adjust the expression and pacing of the generated audio output.
Yes, text-to-speech voice synthesis supports different models for narration and chat. You can choose between expressive, multilingual, or fast models, and set voice controls using environment variables or explicit flags for spoken responses.
The best way to automate spoken audio replies is using a command-line text-to-speech generator that converts written prompts into natural-sounding audio. This avoids manually setting up a TTS workflow for voice messages and explanations.
joeleung0122Generate natural-sounding speech from text using ElevenLabs TTS for local playback.
estebanrfpGenerate natural-sounding speech from text and manage local playback via the sag CLI.
kaivyyTranscribe audio files with OpenAI Whisper and synthesize speech from text.
arthtyagiGenerate spoken audio from text using ElevenLabs models and voice settings.
