Edge TTS

**Quick judgement:** A strong, well-integrated TTS skill that leverages Microsoft Edge’s neural voices for high-quality, multi-language audio. It is suitable as a default TTS solution in Clawdbot, with both a simple path (built-in `tts` tool) and advanced control via Node.js scripts. **What it does well:** - Converts arbitrary text to speech with good voice quality and language coverage. - Offers fine-grained control over voice, language, pitch, rate, volume, and output format. - Supports subtitle (JSON) generation and voice listing. - Provides clear CLI tooling (`tts-converter.js`, `config-manager.js`) and usage docs, including workflow for trigger detection and configuration persistence. **Key risks / limitations:** - **External dependency:** Relies on Microsoft Edge’s online TTS service; failures in network or service availability will break TTS. Requires internet and cannot run fully offline. - **Privacy considerations:** Text is sent to a third-party TTS service; sensitive or confidential content may pose privacy/compliance concerns depending on deployment requirements. - **Temporary file management:** Audio is saved to temp directories and not auto-cleaned; calling applications must manage cleanup to avoid disk bloat. - **No explicit content filtering:** The skill itself does not filter or moderate text; it will attempt to synthesize whatever is passed to it, so moderation must be handled upstream. **Recommended scenarios to enable/use this skill:** - As the primary TTS backend whenever users explicitly request "tts", "text-to-speech", or audio output for responses. - For accessibility-focused deployments (hands-free use, visually impaired users, in-car or multitasking contexts). - For creators needing quick voice-overs where selection of language, specific voice, and quality level matters. - For bots or agents that frequently summarize information and then read it aloud (e.g., news digests, briefings, meeting recaps). Given its maturity, clear documentation, and integration with Clawdbot’s `tts` tool, this skill is a strong candidate for default or recommended TTS functionality, with the caveat that operators consider privacy and implement temp-file cleanup and upstream content moderation where required.