whisper-transcription

To transcribe audio and video files into text, this Skill uses OpenAI's Whisper model to convert spoken media into accurate text transcripts. You simply provide the media file, and it processes the speech-to-text conversion automatically.

You can export subtitles to SRT and VTT formats for video accessibility and SEO, alongside TXT, JSON, and TSV outputs. This allows direct integration of transcribed speech into various media players and platforms.

Yes, you need ffmpeg-python and torch installed to run Whisper transcription, along with the openai-whisper and click libraries. These dependencies provide the underlying model execution and media file handling capabilities.

Yes, you can transcribe multiple audio files at once using the batch processing feature. This allows efficient transcription of multiple media files into text or subtitle formats in a single run.

Yes, the Whisper speech-to-text model supports language translation options. It can transcribe spoken audio from various languages and provide translated text outputs in formats like TXT, SRT, VTT, JSON, or TSV.