LLM Skills
~/catalog/audio & voice//voice-wake-say
Audio & voiceGitHub source

Voice Wake Say

/voice-wake-say

Speak 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>").

ClawHub communityClawHub community
★5
May 17, 2026
// skill content

Skill created by the community and listed sinceClawHub . Canonical source:https://clawhub.ai/skills/voice-wake-say Version: 1.0.1 Source changelog: Remove device-specific trigger (make generic)

// original public source
https://clawhub.ai/skills/voice-wake-say
License: License not specified. Review the repository before reusing it.
Independent project, not affiliated with Anthropic. This skill remains the property of its original author.
// install this skill
Paste this command in your terminal at the root of your project:
mkdir -p .claude/commands && curl -o ".claude/commands/voice-wake-say" "https://clawhub.ai/skills/voice-wake-say"
Then in Claude Code, type /voice-wake-say to activate it.
open_in_newOpen original source
// save
Save available after sign in.
loginSign in to save
// information
Stars★ 5
UpdatedMay 17, 2026
Format.md
AccessFree
// similar

Skills Audio & voice

View allarrow_forward

songsee

★386.5k

Generate spectrograms + feature panels from audio.

Audio & voice
openclaw

Sherpa ONNX text to speech (TTS)

★386.5k

1. Download the runtime for your OS (extracts into `$OPENCLAW_STATE_DIR/tools/sherpa-onnx-tts/runtime`, default `~/.openclaw/tools/sherpa-onnx-tts/runtime`)

Audio & voice
openclaw

Text to speech (ElevenLabs TTS)

★386.5k

Use `sag` for ElevenLabs TTS with local playback.

Audio & voice
openclaw

OpenAI transcriptions API

★386.5k

Transcribe audio through `/v1/audio/transcriptions`. Set `OPENAI_BASE_URL` for an OpenAI-compatible proxy or local gateway.

Audio & voice
openclaw