amber-phone-capabilitiesGive your OpenClaw agent real phone capabilities. Setup uses a short wizard; after setup, run calls and phone tasks with one natural-language prompt.
Install via ClawdBot CLI:
clawdbot install batthis/amber-phone-capabilitiesGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
process.env.OPENAIPotentially destructive shell commands in tool definitions
exec(Calls external URL not in known-safe list
https://github.com/batthis/amber-openclaw-voice-agentUses known external API (expected, informational)
api.openai.comUsage Guide
Loading usage data… refresh in a few seconds.
Scored Jun 5, 2026
AI Analysis
The skill requires legitimate API credentials (Twilio, OpenAI) for its stated phone functionality and uses known external services appropriately. While it accesses sensitive environment variables and executes shell commands, these appear necessary for runtime operations and setup. No evidence of hidden malicious instructions, credential harvesting, or data exfiltration beyond the declared purpose.
Audited Apr 19, 2026 · audit v1.0
Local speech-to-text with the Whisper CLI (no API key).
ElevenLabs text-to-speech with mac-style say UX.
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
Any-to-any AI sub-agent — research, images, video, audio, music, podcasts, avatars, voice cloning, documents, spreadsheets, dashboards, 3D models, diagrams,...
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>").
High-quality voice synthesis with 18 personas, 32 languages, sound effects, batch processing, and voice design using ElevenLabs API.