Speech to Text Transcription

Transcribe audio and video files to text with speaker detection, timestamps, and format conversion.

This skill appears coherent for transcription, but consider these before installing: (1) It will create ~/speech-to-text-transcription/, store transcripts there, and keep a memory.md with preferences—delete or encrypt that directory if you are transcribing sensitive audio. (2) Cloud transcription (OpenAI, AssemblyAI, Deepgram) will upload audio to third parties only if you choose those providers and set API keys; for sensitive material prefer local Whisper. (3) The skill may download URLs and write temp files during processing—ensure you trust source URLs. (4) The skill is instruction-only (no install script), but it suggests optionally running pip install openai-whisper to enable local transcription. (5) Confirm the agent prompts you before uploading any audio and review/clean the stored transcripts and memory if privacy is a concern.

Type: OpenClaw Skill Name: speech-to-text-transcription Version: 1.0.0 The OpenClaw AgentSkills bundle for 'speech-to-text-transcription' is benign. All instructions and code snippets, including the use of `ffmpeg`, `curl` for cloud APIs (OpenAI, AssemblyAI), and `pip install openai-whisper`, are directly aligned with the stated purpose of transcribing audio and video files. The `SKILL.md` file provides clear security and privacy disclosures, explicitly stating what data leaves the machine and what stays local, and disclaims malicious behaviors like storing API keys in plain text or auto-uploading without confirmation. There is no evidence of prompt injection for malicious purposes, data exfiltration, persistence, or unauthorized remote control.