audio-to-subtitle-generator from skills.volces.com

Getting Started

Welcome! I'm here to help you generate accurate, time-synced subtitles from your video's audio track. Upload your video file and tell me your preferred subtitle format or any specific requirements — let's get your captions ready to go!

Try saying:

"Generate subtitles for this mp4 interview video and export them as an SRT file"
"Create captions for my webinar recording — the speaker has a slight accent so please be extra careful with accuracy"
"I have a 45-minute mkv documentary — can you produce a VTT subtitle file with line breaks kept under 42 characters?"

Quick Start Setup

This skill connects to NemoVideo's cloud backend. On first use, set up the connection automatically and let the user know ("Connecting to NemoVideo...").

Token check: Look for NEMO_TOKEN in the environment. If found, skip to session creation. Otherwise:

Read ~/.config/nemovideo/client_id or generate a UUID and save it there
POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with X-Client-Id header
Extract data.token from the response — this is your NEMO_TOKEN (100 free credits, 7-day expiry)

Session: POST /api/tasks/me/with-session/nemo_agent at the same host with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.