Transcribe audio to text locally with Whisper CLI, no API key required.
Overall this appears low risk: it describes local Whisper CLI transcription with no API key, and processing is mainly performed on-device. The main cautions are first-run model downloads and inconsistent/incomplete source metadata, so the repository and release source should be verified before use.
The material explicitly states there are no required keys or environment variables, and the README describes local CLI transcription with no API key. No credential collection, upload, or abuse indicators are shown.
Although no fixed remote endpoint is declared, the README says models are downloaded to ~/.cache/whisper on first run, implying one-time or on-demand outbound network activity. The download source domains are not specified in the material and should be verified during deployment.
Based on the provided material, this looks like usage guidance for an existing `whisper` CLI. It does not show the skill itself requesting extra system privileges, running arbitrary scripts, or starting processes unrelated to its stated function.
Functionally it needs to read user-specified local audio files and write transcription output to a chosen directory; it also writes model cache data to ~/.cache/whisper. The material does not show broader file access beyond this purpose, but local file read/write is involved.
Positive signals include the open-source label and high community trust, but the provenance metadata is incomplete and inconsistent: the name is 'openai-whisper' while the repository link points to `openclaw/openclaw`, with no declared license and unknown maintenance status. Auditability therefore requires manual verification, so this is best rated as caution rather than high risk.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "openai-whisper" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/openclaw/main/skills/openai-whisper/SKILL.md 2. Save it as ~/.claude/skills/openai-whisper/SKILL.md 3. Reload skills and tell me it's ready
Use openai-whisper to transcribe this interview audio into Simplified Chinese text and format it into natural paragraphs.
A Chinese interview transcript organized into readable paragraphs.
First transcribe this meeting recording with openai-whisper, then extract key topics, decisions, and action items into a draft summary.
A draft containing the full transcript and summarized meeting notes.
Use openai-whisper to convert this lecture audio into text, then reorganize it into bullet-point study notes.
A lecture transcript plus structured study notes for review.
Use whisper to transcribe audio locally.
Quick start
whisper /path/audio.mp3 --model medium --output_format txt --output_dir .whisper /path/audio.m4a --task translate --output_format srtNotes
~/.cache/whisper on first run.--model defaults to turbo on this install.Transcribe audio into text or speaker-separated transcripts with OpenAI APIs.
Automate web page workflows, login checks, tab handling, and recovery steps.
Generate concept, architecture, flow, and whiteboard diagrams in multiple formats.
Helps maintainers triage, clean up, and resolve OpenClaw secret scanning alerts.
Investigate test memory growth, heap leaks, and OOM root causes.
Run, debug, monitor, and summarize OpenClaw release CI workflows.
Transcribe audio into multilingual text with optional GPT-based post-processing.
Convert text into voiceovers, accessibility reads, and batch audio prompts.
Convert text to speech locally and offline with sherpa-onnx, no cloud needed.
Transcribe local audio with speaker diarization into structured text directly in AI tools.
Read, search, and analyze WhatsApp chats, voice notes, and images locally.
Connect to TypeWhisper on macOS for transcription, history search, and dictionary management.