Generate speech from text using the ElevenLabs API via the sag CLI tool.
npx skills add https://github.com/yunseo-kim/agent-toolbox --skill sag-tts
Please help me install this Agent Skill. Skill: sag-tts Source: https://github.com/yunseo-kim/agent-toolbox/tree/main/catalog/skills/sag-tts Command: npx skills add https://github.com/yunseo-kim/agent-toolbox --skill sag-tts
This Skill provides a command-line interface for generating speech from text using ElevenLabs, offering a user-friendly experience similar to macOS's built-in 'say' command.
Use sag to speak the phrase "Hello there" with the default voice.
High-intent search queries and answers about installing and using this skill.
To generate speech from text, you use the sag CLI tool to send text to the ElevenLabs API, which returns an audio file. It provides a macOS say-like experience directly from your terminal.
Yes, an ElevenLabs API key is required for operation. You must provide this key to authenticate your requests when generating speech audio from text using the sag CLI tool.
Yes, you can control pronunciation, speed, and intonation using text normalization and audio tags. Audio tagging allows you to enhance speech with expressive emotions like whispering, shouting, or laughing.
The best way to generate natural-sounding audio for a podcast segment is using the sag CLI with ElevenLabs models. It supports voice customization and audio tagging to produce expressive narration.
Yes, the sag CLI tool supports multiple voices and ElevenLabs models for text-to-speech generation. You can select from a range of voices to customize your audio output.
douglasjsGenerate spoken audio from text via the ElevenLabs API.
tony2015116Synthesize and clone voices with MiniMax Voice API and FFmpeg.
aztr0nutzsGenerate speech, transcribe audio, clone voices, and dub audio via the ElevenLabs API.
hasnaGenerate MP3 audio from text using ElevenLabs, OpenAI TTS, or Google Text-to-Speech.
