TTS WhatsApp
ReviewAudited by ClawScan on May 10, 2026.
Overview
The skill’s documented behavior matches its purpose, but it can send WhatsApp messages through your account and relies on external tools you should verify.
This appears coherent for generating and sending WhatsApp voice messages. Before installing, verify the external dependencies and any cloned code, test with --no-send, set the default target carefully, and confirm recipients before sending to individuals or groups.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A mistaken message, target number, or group ID could send an unintended voice message from your WhatsApp account.
Sending WhatsApp voice messages, including to groups, is the core feature and is disclosed, but it is an external action with social/account impact.
- 📤 **Automatic sending** via Clawdbot; - 👥 **Group support** - Send to individuals or WhatsApp groups
Use --no-send for testing, confirm the recipient or group ID, and review the text before allowing automatic delivery.
The workflow can act through your WhatsApp identity and may expose recent WhatsApp message metadata/content during setup.
The skill relies on a WhatsApp-connected Clawdbot account and documents reading WhatsApp channel messages to discover group IDs.
✅ **WhatsApp** connected to Clawdbot ... clawdbot message read --channel whatsapp
Install only where you trust the local Clawdbot WhatsApp setup, and avoid granting access to accounts or groups you do not want the agent to use.
You may run or download code/models that were not included in this submitted skill package.
The setup uses external, unpinned package/model downloads and a manual clone path. These steps are user-directed and purpose-aligned, but users should verify sources.
pip3 install --user piper-tts ... git clone https://github.com/clawdbot/clawdhub.git temp ... wget https://huggingface.co/rhasspy/piper-voices/resolve/main/...
Install dependencies from trusted sources, prefer pinned versions or checksums when available, and inspect any cloned implementation before running it.
Sensitive message content could remain on disk longer than expected if sending fails.
Generated audio files can contain the user’s message content and may remain locally after failed sends or until a later cleanup run.
- **Auto-delete after send** ... - **Auto-cleanup old files** ... - **Keep on error** - Files preserved if sending fails
Avoid sending highly sensitive text unless you are comfortable with temporary local files, and manually clean generated files after failures if needed.