domains / families / media / whisper-transcription

whisper-transcription

separate

Transcribe audio/video to text with word-level timestamps using OpenAI Whisper. Use when you need speech-to-text with accurate timing information for each word.

When to use

Transcribe audio to text
Transcribe video to text
Get word-level timestamps
Detect specific words
Find filler words
Detect multi-word phrases

Skill page

Source

Repository	Path
benchflow-ai/skillsbench	`tasks-extra/video-filler-word-remover/environment/skills/whisper-transcription/SKILL.md`