asr-skill基于Qwen3-ASR-0.6B的语音转文字Skill，支持22种中文方言和多语言识别，让你可以用方言和OpenClaw交流。
Install via ClawdBot CLI:
clawdbot install yszheda/asr-skillGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → http://localhost:3000/transcribePotentially destructive shell commands in tool definitions
rm -rf ~Calls external URL not in known-safe list
http://localhost:3000AI Analysis
The skill processes audio locally (localhost:3000) with stated privacy protections, and while the rule-based signals flagged local endpoints and shell commands, these appear consistent with legitimate local service operation and cleanup. No evidence of unauthorized external data transmission, credential harvesting, or hidden malicious instructions was found in the provided definition.
Generated Mar 20, 2026
This skill enables call centers to handle customer inquiries in various Chinese dialects, automatically transcribing voice calls into text for analysis or routing. It reduces language barriers and improves response times, especially in regions with diverse linguistic populations.
Hospitals and clinics can use this skill to transcribe patient voice notes or consultations in local dialects, ensuring accurate medical records without requiring staff to understand every dialect. It enhances accessibility and data accuracy in multilingual healthcare settings.
Online learning platforms can integrate this skill to transcribe educational content or student responses in dialects, making courses more inclusive for non-Mandarin speakers. It supports personalized learning and feedback in diverse linguistic environments.
Media companies can use this skill to transcribe interviews, podcasts, or videos in Chinese dialects for subtitling, translation, or content analysis. It streamlines production workflows and expands audience reach across dialect-speaking communities.
Government agencies can deploy this skill in public service hotlines or kiosks to transcribe citizen inquiries in dialects, improving service delivery and accessibility. It helps bridge communication gaps in multilingual public administration.
Offer this skill as a cloud-based service with tiered pricing based on usage volume, such as per-minute transcription or API calls. It targets businesses needing scalable, on-demand dialect recognition without infrastructure management.
Sell licenses for on-premise deployment to organizations with strict data privacy requirements, such as healthcare or government. This model includes upfront fees and optional support contracts for local installation and maintenance.
Partner with existing platforms like CRM systems, call center software, or e-learning tools to embed this skill as a value-added feature. Revenue is generated through revenue-sharing agreements or per-integration fees.
💬 Integration Tip
Ensure environment variables like PORT and MODEL_NAME are configured correctly for seamless deployment, and test with sample audio files to verify dialect recognition accuracy.
Scored Jun 17, 2026
Audited Apr 16, 2026 · audit v1.0
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...