Transcribe local audio files to text using the Whisper CLI.
npx skills add https://github.com/hcnimi/clawdis --skill openai-whisper-hcnimi
Please help me install this Agent Skill. Skill: openai-whisper Source: https://github.com/hcnimi/clawdis/tree/main/skills/openai-whisper Command: npx skills add https://github.com/hcnimi/clawdis --skill openai-whisper-hcnimi
Transcribing audio manually is time-consuming and error-prone, especially for long recordings or batches. Running transcription services in the cloud can raise privacy concerns; Whisper CLI enables on-device transcription without API keys, keeping data local.
Transcribe a local audio file using whisper with a chosen model to generate a text transcript.
High-intent search queries and answers about installing and using this skill.
You can transcribe audio files locally by using the Whisper CLI, which processes speech-to-text entirely offline on your device without requiring network access or API keys.
Offline speech-to-text via the Whisper CLI supports transcribing lectures, interviews, podcasts, and meeting recordings directly on personal devices to generate text transcripts.
Local transcription requires installing the Whisper CLI and selecting a Whisper model, allowing on-device processing of common audio formats like mp3, wav, and m4a.
Offline transcription works entirely on your device, keeping audio data local without network access, which prevents privacy concerns associated with cloud-based transcription services.
Choosing a Whisper model for local audio transcription involves selecting from available options to balance speed and accuracy when processing audio files via the Whisper CLI.
dakshrawat298-gifTranscribe local audio files into text or SRT/VTT captions using the Whisper CLI.
yangtaihong59Expose SiYuan note and block management through MCP actions.
imchangchangTranscribe audio files locally using Whisper models via Whisper.cpp.
JiayueMeng128Transcribe and translate audio files locally using the Whisper CLI.
