clawdbot-skill-voice-wake-saySpeak responses aloud on macOS using the built-in `say` command when user input indicates Voice Wake/voice recognition (for example, messages starting with "User talked via voice recognition on <device>").
Install via ClawdBot CLI:
clawdbot install xadenryan/clawdbot-skill-voice-wake-sayUse macOS say to read the assistant's response out loud whenever the conversation came from Voice Wake/voice recognition. Do not use the tts tool (it calls cloud providers).
say (CHECK EVERY MESSAGE INDIVIDUALLY)IF the user message STARTS WITH: User talked via voice recognition on m3
say first (so the user knows you heard them)IF the user message does NOT start with that exact phrase
say. Text-only response only.Critical:
1) Detect Voice Wake context
User talked via voice recognition on m32) Prepare spoken text
3) Speak with say (local macOS TTS)
printf '%s' "$SPOKEN_TEXT" | say
Optional controls (use only if set):
printf '%s' "$SPOKEN_TEXT" | say -v "$SAY_VOICE"
printf '%s' "$SPOKEN_TEXT" | say -r "$SAY_RATE"
say is unavailable or errors, still send the text response and note that TTS failed.Generated Mar 1, 2026
Users can control smart home devices via voice commands on macOS, such as adjusting lights or thermostats. The skill reads back confirmation aloud, providing hands-free feedback for tasks initiated through voice recognition on the m3 device.
In a call center, agents use voice input on macOS to query information or update records. The skill speaks responses aloud, allowing agents to multitask without looking at the screen, improving efficiency in handling customer inquiries.
Individuals with visual impairments interact with their macOS computer using voice commands. The skill converts text responses to speech via the say command, enabling accessible access to information and applications without relying on screen readers.
Presenters use voice commands on macOS to navigate slides or trigger media during presentations. The skill provides spoken feedback, helping presenters stay focused on the audience while managing their presentation tools hands-free.
Analysts in data-driven industries use voice input to request reports or insights from databases. The skill reads out key findings or summaries aloud, facilitating quick decision-making during meetings or while working on other tasks.
Offer the skill as part of a monthly subscription service for businesses, providing regular updates and premium features like custom voice options. Revenue is generated through tiered pricing based on usage levels and integration capabilities.
Sell the skill as a standalone software license for individual users or small teams, with a single upfront payment. This model targets users who prefer ownership without ongoing costs, with potential for add-ons or support packages.
Provide a basic version of the skill for free to attract users, with advanced features like additional voice controls or integration options available for purchase. Revenue comes from users upgrading to premium features within the application.
💬 Integration Tip
Ensure the macOS say command is installed and accessible; test trigger phrases thoroughly to avoid false activations in non-voice contexts.
Turn your AI into JARVIS. Voice, wit, and personality — the complete package. Humor cranked to maximum.
Local Voice Input/Output for Agents using the AI Voice Agent API.
Transcribe audio files using OpenAI's gpt-4o-mini-transcribe model with vocabulary hints and text replacements. Requires uv (https://docs.astral.sh/uv/).
本地生成 Telegram 语音消息,支持自动清洗、分段与临时文件管理。
向指定 Telegram 群组发送语音消息
Generate Russian male voice audio using ComfyUI with Qwen3 TTS node and save as MP3 for voice messages.