voice-wakeSpeak responses aloud on macOS using the built-in `say` command when user input indicates Voice Wake/voice recognition (for example, messages starting with "...
Install via ClawdBot CLI:
clawdbot install kieferhuan/voice-wakeGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Oct 3, 2026
A macOS user enables Voice Wake and dictates requests like "User talked via voice recognition on MacBook." The agent detects the trigger phrase, immediately acknowledges audibly via `say`, completes the task, and optionally speaks a completion summary while the full details remain on screen.
Users with visual impairments or mobility limitations interact with their Mac through Voice Wake and need spoken feedback for every response. The skill checks each message for the exact trigger prefix, then uses local `say` TTS to read a concise, markdown-stripped version of the response aloud.
A Mac mini in a living room or kitchen acts as a voice terminal, receiving input from a wake-word front-end that prepends "User talked via voice recognition on <device>." The skill acknowledges spoken commands first, executes smart-home or info tasks, and speaks results without sending audio to cloud TTS providers.
A developer working in terminal-heavy workflows uses Voice Wake to issue coding or system commands while away from the keyboard. The skill speaks a brief acknowledgment, processes the request, and reads a short spoken summary instead of reading code blocks aloud, keeping sensitive long output off the speaker.
Technicians wearing headsets at remote sites use Voice Wake to log observations and get confirmations hands-free. The agent checks the latest message for the trigger phrase, speaks an immediate confirmation, and reads back short task results over the Mac's local audio output.
A subscription add-on for existing AI assistant or workflow products that adds a local macOS voice-output layer for Voice Wake conversations. Customers pay monthly for seamless spoken acknowledgments and summaries without cloud TTS usage.
License the Voice Wake Say skill to hardware makers, accessibility software vendors, or enterprise IT teams that deploy managed macOS fleets. The license covers integration, updates, and compliance-friendly local TTS behavior.
Offer the core voice-response skill free to individual macOS users while selling a pro tier with multi-device sync, custom voice controls, and enterprise administration. The free version drives adoption and the paid tier monetizes power users and teams.
💬 Integration Tip
Always check the very start of each incoming message for the exact phrase "User talked via voice recognition" because context does not carry over; acknowledge with local `say` before starting longer tasks so users know they were heard.
Scored Oct 3, 2026
Transcribe audio files with speaker diarization (who speaks when). Supports 100+ languages, automatic language detection, and timestamps. Use for meetings, interviews, podcasts, or voice messages. Requires AssemblyAI API key.
使用 poocr 库识别发票并导出 Excel。当用户需要识别增值税发票、批量处理发票文件或提取发票信息到 Excel 时调用此技能。
Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano...
Create, manage, and deploy ElevenLabs conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.
Voice note transcription and archival for OpenClaw agents. Powered by Deepgram Nova-3. Transcribes audio messages, saves both audio files and text transcript...
Text-to-Speech (TTS) and Speech-to-Text (ASR) using coze-coding-dev-sdk. Returns results directly to stdout.