funasr-transcribe-skillUse when the user needs local speech-to-text transcription for audio files, especially Chinese or mixed Chinese-English audio, without relying on cloud trans...
Install via ClawdBot CLI:
clawdbot install limboinf/funasr-transcribe-skillGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/limboinf/funasr-transcribe-skillAudited Apr 16, 2026 · audit v1.0
Generated Mar 22, 2026
Researchers transcribing interviews or lectures in Chinese or mixed languages for qualitative analysis, ensuring data privacy by keeping audio local. This skill avoids cloud API costs and supports dialect-heavy content common in field studies.
Law firms or legal professionals converting client audio recordings, such as witness statements in Chinese, into text for case files. Local processing maintains confidentiality and compliance with data protection regulations without relying on external services.
Content creators generating subtitles for videos with Chinese or mixed-language audio, like documentaries or podcasts, using offline transcription to reduce costs and streamline workflows. It handles various audio formats and integrates into editing pipelines.
Medical practitioners transcribing patient consultations in Chinese dialects for electronic health records, ensuring sensitive health data stays on-premises. This supports accurate documentation without cloud dependencies, ideal for privacy-focused clinics.
Companies recording and transcribing internal meetings with Chinese-English discussions for minutes and action items. Local use avoids subscription fees and data leaks, suitable for organizations with strict IT policies on external APIs.
Offer this skill as a free component within a larger paid software suite for transcription or audio editing, upselling advanced features like batch processing or GPU acceleration. Revenue comes from premium subscriptions or enterprise licenses.
Provide services to businesses for integrating and customizing the skill into their existing workflows, such as adding support for specific dialects or automating transcript exports. Charge per project or hourly for setup and maintenance.
Sell pre-configured devices or servers with this skill installed for offline transcription, targeting industries like legal or healthcare where data security is critical. Revenue is generated from hardware sales and optional support packages.
💬 Integration Tip
Ensure Python 3.7+ is installed and network access is allowed for initial setup; use the provided scripts to automate dependency installation and model downloads for seamless integration.
Scored Jun 19, 2026
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.
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...
Create, manage, and deploy ElevenLabs conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.
Voice note transcription and archival for OpenClaw agents. Powered by Deepgram Nova-3. Transcribes audio messages, saves both audio files and text transcript...
Text-to-Speech (TTS) and Speech-to-Text (ASR) using coze-coding-dev-sdk. Returns results directly to stdout.