qwen-asr-skillProvides high-accuracy speech-to-text conversion supporting 22 Chinese dialects and 30 languages with automatic language detection, running on CPU.
Install via ClawdBot CLI:
clawdbot install yszheda/qwen-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/transcribeCalls external URL not in known-safe list
http://localhost:3000AI Analysis
The skill processes audio locally and sends data only to localhost (http://localhost:3000), which is consistent with its stated purpose of local transcription. No evidence of unauthorized external data exfiltration, credential harvesting, hidden instructions, or obfuscation was found in the provided definition.
Audited Apr 17, 2026 · audit v1.0
Generated Mar 20, 2026
Transcribes customer service calls in various Chinese dialects to text for analysis and record-keeping. Helps businesses understand regional customer needs and improve service quality without storing sensitive audio data.
Converts educational audio or video lectures in Chinese dialects into text for subtitles or transcripts. Makes learning materials accessible to students who speak different dialects or are hearing-impaired.
Transcribes patient-doctor conversations in local dialects for accurate medical records. Ensures privacy by processing audio locally and deleting it after transcription, complying with data protection regulations.
Generates subtitles for videos, podcasts, or live streams in multiple Chinese dialects and languages. Enables content creators to reach broader audiences with minimal setup and no GPU requirements.
Transcribes legal proceedings, government meetings, or public announcements in dialects to create official text records. Supports local governance and legal accuracy with on-premise processing for security.
Offer the ASR service as a cloud-based API with tiered pricing based on usage volume (e.g., per minute of audio). Targets businesses needing scalable, on-demand transcription without hardware investment.
Sell licenses for local deployment to organizations with strict data privacy requirements, such as healthcare or government. Includes support and updates for the skill package.
Provide a free basic version with limited features (e.g., shorter audio duration) and charge for advanced capabilities like higher accuracy, longer audio support, or priority processing in the full version.
💬 Integration Tip
Ensure the host system has at least 8GB RAM and a multi-core CPU for optimal performance, and verify audio format compatibility before deployment.
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...