π¦ ClawHub
Voice Reply Mode
by @nasplycc
Enables agents to reply in the same modality as received: voice messages get voice replies, text messages get text replies, using Edge TTS and config snippets.
TERMINAL
clawhub install voice-reply-modeπ About This Skill
name: voice-reply-mode description: Add same-modality conversation behavior to an agent: voice in β voice out, text in β text out. Use when enabling Telegram/Feishu voice-note workflows with Edge TTS, documenting agent voice preferences, and providing gateway config snippets for inbound-only TTS auto replies.
Voice Reply Mode
Use this skill when a user wants an agent to behave like this:
What this skill includes
SOUL.md / IDENTITY.md / TOOLS.mdmessages.ttsImportant boundary
This skill can package rules, scripts, and config snippets.
It does not automatically change a user's global gateway config unless the user explicitly asks and authorizes it.
Recommended workflow
1. Read references/workspace-snippets.md
2. Read references/gateway-config.md
3. Copy the relevant snippets into the target agent workspace
4. If the user explicitly asks, patch gateway config with the snippet from references/gateway-config.md
5. Validate with one text message and one voice message
Minimal success criteria
Files in this skill
references/workspace-snippets.md β snippets for IDENTITY.md, SOUL.md, TOOLS.mdreferences/gateway-config.md β messages.tts examples and caveatsreferences/channel-notes.md β Telegram / Feishu notesscripts/edge-tts.sh β helper script for local TTS generationNotes
messages.tts.auto = "inbound".identity.voice, keep voice preference in workspace docs instead.π Tips & Best Practices
messages.tts.auto = "inbound".identity.voice, keep voice preference in workspace docs instead.