Transcribes audio files to text locally using the Whisper CLI.
npx skills add https://github.com/Cyandex/ErnOS --skill openai-whisper-cyandex
Please help me install this Agent Skill. Skill: openai-whisper Source: https://github.com/Cyandex/ErnOS/tree/main/skills/openai-whisper Command: npx skills add https://github.com/Cyandex/ErnOS --skill openai-whisper-cyandex
whisper CLI. - Translation: Use the --task translate option to translate foreign-language audio into English subtitles (SRT). - Model Size Control: Choose smaller models for speed or larger models for accuracy; models download once to ~/.cache/whisper. - Use Case: You recorded a one-hour meeting as an M4A file. Run Whisper locally to produce a text transcript and subtitle file without uploading the recording to any external service. ## Quick Start Ask the assistant to transcribe a local audio file, for example: transcribe meeting.mp3 with Whisper using the medium model and save the output as a text file.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 to the output directory you specify.
Use the --task translate flag with an SRT output format, for example: whisper audio.m4a --task translate --output_format srt. Whisper translates the speech into English and writes a subtitle file.
No API key is needed because Whisper runs entirely locally. Internet access is only required once per model, since models download to ~/.cache/whisper on first run and are cached afterward.
Use smaller models for faster transcription and larger models for higher accuracy. On this install the default model is turbo, and you can override it with the --model flag, such as --model medium.
The whisper binary must be installed first, for example via Homebrew with the openai-whisper formula. After installation, verify the whisper command is available on your PATH before transcribing.
felipesantiago-coderConvert base64 encoded audio files into written text transcriptions.
RonanCodesExtract and clean YouTube video transcripts from SRT files.
JigsawStackConvert spoken audio into searchable transcripts with timestamps and speaker labels.
TikTzukiConvert text to speech and transcribe audio via cloud APIs.