Transcribe audio files to text locally using the Whisper CLI.
npx skills add https://github.com/shalevamin/Tau_agent --skill openai-whisper-shalevamin
Please help me install this Agent Skill. Skill: openai-whisper Source: https://github.com/shalevamin/Tau_agent/tree/main/tau-agent-main/skills/openai-whisper Command: npx skills add https://github.com/shalevamin/Tau_agent --skill openai-whisper-shalevamin
--task translate option to translate non-English audio into English subtitles (SRT). - Flexible Model Sizes: Choose smaller models for speed or larger ones for accuracy; models download once to ~/.cache/whisper. - Use Case: You recorded a one-hour meeting as an M4A file. Run Whisper with the medium model to produce a searchable text transcript without uploading anything to the cloud. ## Quick Start Transcribe the attached audio file meeting.m4a into a text file using Whisper with the medium model.High-intent search queries and answers about installing and using this skill.
Run whisper followed by the audio file path, for example: whisper /path/audio.mp3 --model medium --output_format txt --output_dir . The transcript is written as a text file to the output directory.
Use the --task translate flag with SRT output: whisper /path/audio.m4a --task translate --output_format srt. Whisper translates non-English speech into English subtitle files.
No, the Whisper CLI runs models locally on your machine and does not need an API key. Models are downloaded once to ~/.cache/whisper on first run and reused afterward.
Use smaller models for faster transcription and larger models for better accuracy. On this install the default model is turbo, and you can override it with the --model flag, such as --model medium.
The first run downloads the selected model weights to ~/.cache/whisper, which can take time depending on model size and network speed. Subsequent runs load the cached model directly.
first-flukeGenerates local text-to-speech audio and transcribes audio files via the Voicebox MCP server.
Wanli-LeeFetch cleaned subtitle transcripts from YouTube or Bilibili videos.
garochee33Transcribe audio and video recordings into text with speaker diarization.
framerslabTranscribe live speech in real time using the OpenAI Whisper API.