OpenClaw Voice Synthesis

Generate a local speech file from text using macOS built-in TTS, with a simple and repeatable workflow.

This skill is for voice generation itself. It does not require the audio to be sent into chat, although the generated file can be handed off to a channel-send workflow afterwards.

What this skill does

Use macOS built-in tools to produce a spoken audio artifact:

• say for text-to-speech generation
• afconvert for converting the result into a more convenient output format such as .wav

This skill is for:

• turning text into speech
• generating a reusable local audio file
• preparing a voice file for later delivery or reuse