webchat-voice-proxy⚠️ DEPRECATED — This skill has been split into two separate skills for better modularity: **webchat-https-proxy** (HTTPS/WSS reverse proxy) and **webchat-voi...
Install via ClawdBot CLI:
clawdbot install neldar/webchat-voice-proxyGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval(Calls external URL not in known-safe list
http://127.0.0.1:18790/transcribe`AI Analysis
The skill only proxies to explicitly local services (127.0.0.1) for transcription and WebSocket connections, with no evidence of data exfiltration to external servers. The primary risks are local privilege escalation via shell commands and dependency on an external Python package (aiohttp), but these align with the skill's stated purpose of enabling local voice input.
Audited Apr 18, 2026 · audit v1.0
Generated Mar 21, 2026
Teams use the voice proxy for hands-free communication during virtual meetings, enabling push-to-talk voice input in WebChat for real-time transcription and seamless integration with collaboration tools. It supports multiple languages, making it ideal for international teams.
Support agents leverage the proxy to transcribe customer voice queries locally, ensuring data privacy while providing quick responses via WebChat. The toggle mode allows for continuous recording during lengthy interactions.
Language tutors use the skill to offer voice-based exercises where students speak into the mic for real-time transcription and feedback in their native language, enhancing interactive learning sessions.
Medical professionals utilize the proxy for dictating patient notes via voice input, with local transcription ensuring HIPAA compliance and secure handling of sensitive information through HTTPS.
Developers integrate the proxy to add voice command capabilities to IoT devices via WebChat, using push-to-talk for precise control and keyboard shortcuts for hands-free operation in smart home setups.
Offer basic voice transcription and WebChat integration for free, with premium features like advanced language support, higher accuracy, and team collaboration tools for a monthly subscription fee.
Provide customized deployments for large organizations, including dedicated support, enhanced security features, and integration with existing enterprise systems, sold through annual licenses.
Distribute the skill as open source, generating revenue through consulting services, custom development, and training workshops for businesses adopting the technology.
💬 Integration Tip
Ensure the faster-whisper service is running locally before deployment to avoid transcription failures, and set environment variables like VOICE_HOST for LAN exposure only on trusted networks.
Scored Apr 19, 2026
Local speech-to-text with the Whisper CLI (no API key).
Transcribe audio files with speaker diarization (who speaks when). Supports 100+ languages, automatic language detection, and timestamps. Use for meetings, interviews, podcasts, or voice messages. Requires AssemblyAI API key.
Turn your AI into JARVIS. Voice, wit, and personality — the complete package. Humor cranked to maximum.
Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch contro...
使用 poocr 库识别发票并导出 Excel。当用户需要识别增值税发票、批量处理发票文件或提取发票信息到 Excel 时调用此技能。
Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano...