livekit-voiceLiveKit real-time voice and video infrastructure — create rooms, generate JWT access tokens, manage participants, and record sessions. Open source WebRTC for...
Install via ClawdBot CLI:
clawdbot install aiwithabidi/livekit-voiceGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://www.agxntsix.aiAudited Apr 18, 2026 · audit v1.0
Generated Mar 22, 2026
Deploy voice AI agents to handle customer inquiries in real-time, reducing wait times and operational costs. The skill enables creating rooms for each call, generating tokens for AI agents and customers, and managing sessions with recording for quality assurance.
Facilitate secure audio/video consultations between patients and healthcare providers using LiveKit's infrastructure. It allows creating private rooms, managing participant access with tokens, and recording sessions for medical records compliance.
Build a platform where learners practice conversations with AI tutors in real-time voice rooms. The skill supports creating sessions, generating tokens for learners and AI tutors, and integrating with STT/TTS services for natural interactions.
Host live audio/video events such as webinars or conferences with participant management and recording capabilities. Use the skill to create rooms, issue access tokens to attendees and speakers, and record sessions for on-demand viewing.
Enable voice and video meetings for distributed teams with features like room creation, participant management, and session recording. The skill integrates with AI tools for transcription or translation to enhance collaboration.
Offer a managed service using LiveKit Cloud to provide voice AI infrastructure to businesses, charging monthly or annual fees based on usage metrics like room hours or participant counts. This model leverages the skill's API for easy integration and scalability.
Provide expertise in setting up and customizing LiveKit for clients, such as integrating with existing voice AI tools or developing bespoke solutions. Revenue comes from project-based fees or ongoing support contracts, utilizing the skill's commands for deployment.
Monetize by offering recording and analytics services for voice sessions, using the skill's record command to capture audio/video and process data for insights. Charge clients based on recording duration or data analysis volume.
💬 Integration Tip
Ensure all required environment variables (LIVEKIT_API_KEY, LIVEKIT_API_SECRET, LIVEKIT_URL) are set before running commands, and test token generation with specific grants to control participant permissions effectively.
Scored Apr 19, 2026
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).
Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch control, and subtitle generation. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.
Local text-to-speech via sherpa-onnx (offline, no cloud)
Start voice calls via the OpenClaw voice-call plugin.