Transcribe spoken audio into text transcripts using Whisper models.
npx skills add https://github.com/xuiltul/animaworks --skill transcribe-tool
Please help me install this Agent Skill. Skill: transcribe-tool Source: https://github.com/xuiltul/animaworks/tree/main/templates/ja/common_skills/transcribe-tool Command: npx skills add https://github.com/xuiltul/animaworks --skill transcribe-tool
The transcription tool eliminates manual note-taking by converting spoken audio to accurate text using Whisper models, enabling searchable transcripts and captions.
Call the transcribe tool with an audio_path to convert speech to text.
High-intent search queries and answers about installing and using this skill.
To transcribe audio into text, call the transcribe tool with an audio_path and a Whisper model like large-v3-turbo. You can specify the spoken language and enable optional post-processing to refine the generated transcript for higher accuracy.
Yes, this transcription tool converts spoken audio from meetings, interviews, and podcasts into accurate, editable text transcripts. It eliminates manual note-taking by automating speech-to-text conversion, enabling searchable transcripts and media captions.
GPU acceleration is optional but recommended to speed up Whisper speech-to-text conversion. The core requirement is a Python environment and a Whisper model, while applying GPU processing significantly enhances transcription performance for large audio files.
The best way to improve transcription accuracy is enabling the optional post-processing feature. This refines the initial Whisper speech-to-text output by applying an LLM to correct and enhance the generated text transcripts for higher accuracy.
Yes, Whisper transcription supports language specification to accurately process non-English audio. You can define the spoken language when calling the transcribe tool, ensuring correct text output across different languages for your media files.
sunchenddTranscribe local audio files to text with faster-whisper and optional word-level timestamps.
hmzainjamilConvert audio and video recordings into transcripts, subtitles, and meeting notes.
braselogTranscribe meeting audio into text transcripts with optional speaker diarization.
yunseo-kimTranscribe audio files to text locally using the Whisper CLI.
