wjs-transcribing-audio

SKILLWorkflowcommunity
v0.0.0jianshuoMITUpdated 1d agoSource →

Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano (豆包) ASR; other languages (Spanish, English, Portuguese, French, Italian, Japanese, Korean, etc.) use OpenAI Whisper API with word-level times

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
120Repo stars
1Clients
1Formats
1d agoLast update
Skill
Authorjianshuo
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor
Copilot
ChatGPT
Gemini
About

Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano (豆包) ASR; other languages (Spanish, English, Portuguese, French, Italian, Japanese, Korean, etc.) use OpenAI Whisper API with word-level timestamps and self-assembled cues. Outputs SRT with punctuation-bounded cues capped for on-screen readin

Keywords
skillclaude