voice-assistantReal-time voice assistant for OpenClaw. Streams mic audio through configurable STT (Deepgram or ElevenLabs) into your OpenClaw agent, then speaks the response via configurable TTS (Deepgram Aura or ElevenLabs). Sub-2s time-to-first-audio with full streaming at every stage.
Install via ClawdBot CLI:
clawdbot install charantejmandali18/voice-assistantGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
http://localhost:7860Audited Apr 17, 2026 · audit v1.0
Generated Mar 20, 2026
Deploy as a real-time voice assistant for handling customer inquiries in call centers. Uses Deepgram STT for fast transcription and ElevenLabs TTS for natural-sounding responses, reducing wait times and improving user satisfaction. Integrates with existing OpenClaw agents to access customer data and tools for issue resolution.
Implement in clinics for voice-based patient intake and symptom collection. Leverages ElevenLabs STT for multilingual support to accommodate diverse patients, with Deepgram TTS for low-latency feedback. Streamlines administrative tasks by integrating with OpenClaw to update electronic health records.
Use as a voice interface for controlling IoT devices in smart homes. Combines Deepgram STT and TTS for minimal latency, enabling quick commands like adjusting lights or thermostats. Connects to OpenClaw agents to process natural language requests and trigger automation workflows.
Deploy in language learning apps for interactive speaking practice. Utilizes ElevenLabs TTS for high-quality voice output to model pronunciation, with Deepgram STT for accurate speech recognition. Integrates with OpenClaw to provide personalized feedback and lesson adjustments based on student responses.
Implement in physical stores or e-commerce platforms for voice-guided shopping. Uses Deepgram STT for fast query processing and ElevenLabs TTS for engaging product descriptions. Connects to OpenClaw to access inventory databases and recommend products based on customer preferences.
Offer the voice assistant as a cloud-based service with tiered pricing based on usage minutes or API calls. Includes features like custom voice models and priority support. Targets businesses needing scalable, real-time voice interactions without infrastructure management.
Sell licenses for self-hosted deployments, allowing enterprises to run the assistant on their own servers for data security. Includes setup support and maintenance contracts. Ideal for industries with strict compliance requirements like finance or healthcare.
Generate revenue by charging per API call for STT and TTS services through the integrated providers like Deepgram and ElevenLabs. Offer bundled packages or pay-as-you-go plans. Appeals to developers and startups building custom voice applications with flexible scaling.
💬 Integration Tip
Ensure your OpenClaw gateway is running locally or on a low-latency network to achieve sub-2s response times, and test different provider combinations based on your quality and speed needs.
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.
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...