openclaw-voice-assistantWindows voice companion for OpenClaw. Custom wake word via Porcupine, local STT via faster-whisper, streamed responses over the gateway WebSocket, and ElevenLabs TTS with natural chime/thinking sounds. Supports multi-turn conversation with automatic follow-up listening, mic suppression to prevent feedback, and a system tray with pause/resume. Recommended voices: Matilda (XrExE9yKIg1WjnnlVkGX, free tier) or Ivy (MClEFoImJXBTgLwdLI5n, paid tier). Fully customizable wake word, voice, hotkey, and silence thresholds.
Install via ClawdBot CLI:
clawdbot install kurtivy/openclaw-voice-assistantGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://picovoice.aiAudited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
Enables voice-activated control of smart home devices through OpenClaw, allowing users to issue commands like adjusting lights or thermostats hands-free. The local wake word and STT ensure privacy and responsiveness, while TTS provides audible feedback.
Deploys a voice-based AI assistant for handling customer inquiries in call centers or retail settings, using multi-turn conversation for natural interactions. Custom wake words and voices can be branded to enhance user experience.
Supports interactive learning by allowing students to ask questions verbally and receive spoken explanations, fostering engagement in classrooms or e-learning platforms. The system tray controls enable easy management by educators.
Assists healthcare professionals with voice commands for accessing patient records or scheduling, improving efficiency in clinical environments. Local processing ensures data privacy compliance for sensitive information.
Integrates with business software to enable voice-driven task management, such as scheduling meetings or generating reports, boosting workplace productivity. Hotkey support allows quick activation without disrupting workflow.
Offers the voice assistant as a cloud-based service with tiered pricing for features like custom voices or advanced wake words, targeting businesses needing scalable solutions. Revenue comes from monthly or annual subscriptions.
Licenses the skill package to hardware manufacturers for integration into smart devices like speakers or IoT gadgets, providing a turnkey voice solution. Revenue is generated through one-time licensing fees or royalties per unit sold.
Provides a free basic version with limited voices or wake words, while charging for premium features such as enhanced TTS models or priority support. This model attracts individual users and upsells to power users or small businesses.
💬 Integration Tip
Ensure all required environment variables are set in the .env file and test the gateway connection before deployment to avoid common setup issues.
Scored Jun 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.
Search and manage Spotify playlists, tracks, albums, artists, and playback state via the Spotify Web API. Use this skill when users want to search for music,...
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。
Transcribe long audio files safely on 16GB RAM machines using auto-chunking with Whisper’s base model and seamless transcript merging.
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...