Transcribe spoken audio into text across 99 languages using openai-whisper.
npx skills add https://github.com/unclehowell/unclehowell --skill whisper-unclehowell
Please help me install this Agent Skill. Skill: whisper Source: https://github.com/unclehowell/unclehowell/tree/main/skills/mlops/models/whisper Command: npx skills add https://github.com/unclehowell/unclehowell --skill whisper-unclehowell
Converting spoken audio into accurate, searchable text across many languages, eliminating manual transcription and translation effort.
turbo variant.Transcribe the audio file 'meeting.mp3' to text using the Whisper skill.
High-intent search queries and answers about installing and using this skill.
Multilingual transcription converts spoken audio into text across 99 languages. It processes podcasts, meetings, and video subtitles by leveraging the openai-whisper library, supporting language detection and direct translation of foreign speech into English text.
Python 3.8+ and ffmpeg are required for speech-to-text conversion. GPU acceleration is optional but leverages CUDA for rapid processing of large audio files, allowing faster transcription when handling batch processing or large model variants.
Direct translation converts foreign speech into English text from audio files. It processes spoken language and generates translated transcripts, eliminating manual translation effort while supporting various audio formats for podcasts and meetings.
Batch processing for large audio transcription handles multiple files with a single script. Choosing the fast turbo variant and leveraging GPU acceleration with CUDA ensures rapid processing of large audio files across supported languages.
Audio processing speech recognition supports model flexibility from tiny to large models, including the fast turbo variant. Choosing smaller models speeds up transcription while larger models provide greater accuracy for complex multilingual speech.
icyzhTranscribe and translate audio files into text using OpenAI Whisper.
BrmboboFetch YouTube transcripts via subtitles or Whisper audio transcription.
NITISH-gitbitTranscribe spoken language to text using OpenAI's Whisper model.
fikriafConvert spoken language into written text across multiple languages.