Transcribe local audio files to text or subtitles using the Whisper CLI.
npx skills add https://github.com/nomad3/openclaw-k8s --skill openai-whisper-nomad3
Please help me install this Agent Skill. Skill: openai-whisper Source: https://github.com/nomad3/openclaw-k8s/tree/main/package/skills/openai-whisper Command: npx skills add https://github.com/nomad3/openclaw-k8s --skill openai-whisper-nomad3
It eliminates the need to manually transcribe audio by providing fast local speech-to-text using the Whisper CLI.
Example use case: you record meeting audio and need a readable transcript or subtitle file for review and sharing.
Run whisper /path/audio.mp3 --model medium --output_format txt --output_dir .
High-intent search queries and answers about installing and using this skill.
You can transcribe audio files locally without an API key by running the Whisper CLI on your machine to convert formats like .mp3 and .m4a into text without sending data remotely.
Yes, you can generate subtitle files from speech-to-text output by specifying an output format, allowing you to produce readable transcripts or subtitle files directly from your audio.
You control transcription accuracy versus speed through model selection, choosing smaller Whisper models for faster processing or larger models to achieve better transcription accuracy.
Yes, you need the whisper executable installed on your machine to perform offline speech-to-text, as this process runs entirely through the local Whisper CLI.
Yes, Whisper can translate spoken audio while transcribing, providing optional translation alongside local speech-to-text for common audio file types.
The best way to convert meeting audio into a readable transcript is using local speech-to-text with the Whisper CLI, specifying your audio file, model size, and text output directory.
linuxhsjTranscribe and translate audio files locally using the Whisper CLI.
dawsonblockFetch YouTube transcripts and convert them into chapters, summaries, threads, and blog posts.
mangiapanejohn-devTranscribe audio files to text locally using the Whisper CLI.
Desko77Transcribe audio and video files using local and cloud speech recognition.
