Synthesize summarized Claude responses as speech via edge_tts with a flag-controlled toggle.
npx skills add https://github.com/ahostbr/liteharness --skill ls-tts
Please help me install this Agent Skill. Skill: ls-tts Source: https://github.com/ahostbr/liteharness/tree/main/liteharness/catalog/skills/ls-tts Command: npx skills add https://github.com/ahostbr/liteharness --skill ls-tts
You need a reliable way to have Claude responses read aloud so you can consume answers hands-free, without manually copying text into another tool.
Enable TTS mode by telling the assistant: "ls-tts on".
High-intent search queries and answers about installing and using this skill.
To enable text-to-speech playback for Claude responses, tell the assistant "ls-tts on". This activates a persistent flag-controlled toggle that synthesizes spoken audio summaries of responses on demand.
Yes, hands-free speech synthesis reads concise response summaries aloud automatically. The toggle avoids manually copying text into another tool by using Edge TTS to generate audio after each enabled response.
No, the TTS voice avoids reading technical noise like code blocks and file paths. Speech synthesis only reads summarized non-technical content under 200 characters to ensure quick comprehension.
The text-to-speech mode uses Edge TTS with the en-GB-SoniaNeural voice, known as Sonia. It synthesizes speech and plays the audio back using the playsound playback library.
To turn off spoken response playback, tell the assistant "ls-tts off". This updates the persistent flag file, disabling audio synthesis for subsequent responses during your interactive agent session.
No, text-to-speech is not suitable for long technical reviews. It intentionally limits spoken summaries to non-technical content under 200 characters and skips code blocks, making it best for quick status updates rather than detailed reading.
rahulrajaramConvert input text to spoken audio using the Kokoro TTS engine.
WarrenZhu050413Generate and play multilingual text-to-speech audio with adjustable voices and speeds.
yazelinConvert voice messages to text and generate spoken responses.
kraftvaerkImplement granular user permissions for specific entity types in the Umbraco backoffice.
