usewhisperOfficial Whisper Context skill for OpenClaw. Cuts context tokens via delta compression + caching, and adds long-term memory across sessions.
Install via ClawdBot CLI:
clawdbot install alinxus/usewhisperGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://context.usewhisper.devAudited Apr 17, 2026 · audit v1.0
Generated Mar 22, 2026
A company uses an AI chatbot for customer support to handle repetitive inquiries. By integrating this skill, the chatbot reduces token usage by compressing conversation history with delta compression, maintaining context across sessions for returning users, and storing preferences in long-term memory to personalize responses, cutting API costs significantly.
An online tutoring platform employs an AI assistant to guide students through learning sessions. The skill helps by caching previous interactions to avoid resending full histories, using memory search to recall student progress and preferences, and compressing context to handle long conversations efficiently, enhancing scalability.
A telehealth service uses an AI agent to interact with patients, documenting symptoms and providing follow-up advice. This skill enables secure context compression to manage lengthy medical histories, ingest sessions for compliance records, and search memories for patient-specific data, ensuring cost-effective and accurate interactions.
A fintech firm deploys an AI agent to offer personalized financial advice to clients. By leveraging the skill, the agent compresses complex financial histories, uses oracle search for real-time market research, and writes memories of client risk preferences, optimizing token spend while maintaining detailed, cross-session context.
Offer the skill as part of a subscription-based service for businesses using OpenClaw, charging monthly fees based on usage tiers or number of API calls reduced. Revenue streams include premium features like advanced memory search and priority support, targeting companies with high AI interaction volumes.
Provide consulting services to help enterprises integrate this skill into their existing AI systems, focusing on custom setups, security audits, and performance tuning. Revenue is generated through project-based fees and ongoing maintenance contracts, appealing to large organizations with complex needs.
Deploy a freemium model where basic context compression and memory features are free up to a certain usage limit, with paid upgrades for higher volumes, advanced compression strategies, and analytics. This attracts small to medium businesses, driving conversion through demonstrated cost savings.
💬 Integration Tip
Always call query_context before model interactions to inject compressed context, and use stable user_id and session_id values for effective memory and caching across sessions.
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.