funasr-nano-transcribe使用 Fun-ASR-Nano-2512 轻量级模型进行语音转文字。 提供快速准确的中文语音识别,识别结果实时输出到控制台,针对 CPU/GPU 环境优化。 使用场景:(1) 将中文音频文件转写为文字,(2) 需要轻量级低内存占用的 ASR, (3) 处理包含领域特定热词的音频(医疗、保险等), (4) 需要高准...
Install via ClawdBot CLI:
clawdbot install frozenarctic/funasr-nano-transcribeGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → http://localhost:11890/transcribePotentially destructive shell commands in tool definitions
eval(Calls external URL not in known-safe list
https://download.pytorch.org/whl/cpuAudited Apr 18, 2026 · audit v1.0
Generated Mar 21, 2026
Transcribes patient-doctor audio recordings into structured text for electronic health records, supporting medical terminology and privacy-sensitive offline processing. Enables efficient documentation without manual typing, improving accuracy in clinical notes.
Converts audio from customer calls or field reports into text for claim assessment, using domain-specific keywords to flag relevant details. Facilitates faster claim handling and reduces manual data entry errors in insurance workflows.
Automatically transcribes customer service interactions in Chinese for quality assurance and analytics, optimizing response times with lightweight deployment. Helps identify common issues and train agents based on real conversation data.
Transcribes classroom lectures or online course audio into text for study materials or accessibility purposes, handling academic vocabulary efficiently. Supports educators in creating searchable content from spoken lessons.
Records and transcribes legal proceedings or interviews in Chinese, ensuring accurate text records for case files with offline capability for confidentiality. Aids lawyers in reviewing testimonies without manual transcription costs.
Offers API access to the transcription service via FastAPI on a pay-per-use or monthly subscription basis, targeting businesses needing frequent audio processing. Generates recurring revenue from healthcare or insurance clients requiring scalable, low-latency solutions.
Sells the skill package for offline deployment in secure environments like hospitals or legal firms, with one-time licensing fees and optional support contracts. Appeals to organizations with data privacy concerns or limited internet access.
Partners with software vendors in healthcare or customer service to embed the transcription capability into existing platforms, earning revenue through integration fees or revenue sharing. Leverages the skill's lightweight design for seamless addition to third-party applications.
💬 Integration Tip
Deploy the FastAPI service for high-frequency use to avoid model reload delays, and ensure the 2-3GB memory requirement is met for smooth operation.
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...