qqbot-voice-transcribeQQ Bot 语音消息自动识别 v2.0。自动解码 QQ Silk V3 格式，Whisper medium 模型识别，Gateway 集成，用户确认流程。
Install via ClawdBot CLI:
clawdbot install cindypapa/qqbot-voice-transcribeGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
exec(Calls external URL not in known-safe list
https://github.com/openclaw/skills/qqbot-voice-transcribeAI Analysis
The skill processes audio files locally using open-source tools (silk-v3-decoder, Whisper) and does not send user data to external servers. The primary risk is the use of shell commands (exec) which could be exploited if inputs are not properly sanitized, but the code shows no evidence of credential harvesting, obfuscation, or hidden malicious behavior.
Audited Apr 17, 2026 · audit v1.0
Generated May 8, 2026
在 QQ 群聊中，用户发送语音消息时，机器人自动识别并转换为文字，方便群成员快速浏览消息内容，特别适合信息密集的管理群或学习群。
企业客服在 QQ 上收到客户语音咨询，系统自动将语音转为文本并存储，便于后续分析客户意图、质检客服服务质量。
老师在 QQ 学习群中发送语音讲解，机器人自动转写为文字笔记，学生可随时查看，提高学习效率。
在 QQ 群内进行语音会议或讨论时，机器人自动记录所有语音消息并转为文字，生成会议纪要存档。
为听力障碍用户提供 QQ 语音消息的实时文字显示，使其能正常参与群聊，提升社交包容性。
面向企业和社群管理员提供语音转文字服务，按群数量或识别时长收费，提供 API 集成和 Dashboard 管理。
针对需要私有化部署的企业（如金融、政府），提供一次性授权费，并收取定制开发和技术支持费用。
基础语音转文字免费，但高级功能如多语言识别、关键词高亮、语义分析等需要额外付费。
💬 Integration Tip
集成前确保安装 silk-v3-decoder 和 ffmpeg，并配置 whisper 模型路径；初次运行需编译解码器，约多花30秒。
Scored Jul 2, 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.
Turn your AI into JARVIS. Voice, wit, and personality — the complete package. Humor cranked to maximum.
Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch contro...
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。
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...