tts-autoplayAuto-play TTS voice files with wake word detection. Only plays audio when user message contains wake words like "语音", "念出来", "voice", etc. Perfect for Webcha...
Install via ClawdBot CLI:
clawdbot install wangzjhz/tts-autoplayGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/openclaw/skills/tts-autoplayAudited Apr 16, 2026 · audit v1.0
Generated Mar 21, 2026
Enhance webchat support by providing voice responses only when users explicitly request them, such as by saying 'voice' or 'speak'. This reduces audio clutter while improving accessibility for users who prefer spoken feedback, ideal for handling FAQs or troubleshooting steps in real-time.
Use in online learning platforms to read aloud educational materials like news or stories when students ask with wake words like 'read it' or '念出来'. This supports multimodal learning by offering text-based responses by default and voice on demand, catering to diverse learning preferences.
Integrate with home automation systems to provide voice feedback for queries like weather updates or news, triggered by phrases such as '用语音' or 'say it'. This allows for silent operation most of the time, conserving resources and reducing noise, while delivering audio when needed for hands-free interaction.
Deploy in assistive applications to convert text responses to speech only when users invoke it with wake words like '语音' or 'read aloud'. This ensures that voice output is user-controlled, enhancing usability without overwhelming users with constant audio, perfect for navigation or information retrieval tasks.
Apply in gaming or entertainment bots to deliver voice lines for story narration or character dialogues when players use triggers like '讲个故事给我听'. This adds immersive audio elements on demand, keeping text interactions fast and efficient while enhancing engagement during key moments.
Offer a basic version with default wake words for free to attract users, then charge for premium features like custom wake word lists, advanced detection modes, or integration with enterprise systems. Revenue comes from subscription tiers, targeting small businesses and developers seeking scalable voice solutions.
License the skill to hardware manufacturers or software platforms (e.g., smart devices, chat applications) for embedding as a voice response module. Revenue is generated through one-time licensing fees or royalties per unit, leveraging the skill's lightweight design and wake word detection for seamless integration.
Provide services to customize the skill for specific industries, such as adding industry-specific wake words, time-based controls, or enhanced security features. Revenue comes from project-based contracts and ongoing support, catering to organizations needing tailored voice automation solutions.
💬 Integration Tip
Ensure TTS is configured in 'tagged' mode in openclaw.json and test wake word detection with the provided PowerShell scripts to avoid playback issues.
Scored Apr 19, 2026
Local speech-to-text with the Whisper CLI (no API key).
ElevenLabs text-to-speech with mac-style say UX.
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch control, and subtitle generation. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.
Local text-to-speech via sherpa-onnx (offline, no cloud)
Start voice calls via the OpenClaw voice-call plugin.