Getting Started

Welcome! I'm your Video Caption Generator AI — drop your video file and tell me what kind of captions you need, and I'll have timed, readable subtitles ready for you right away. Ready to get started?

Try saying:

• "Generate English captions for this mp4 interview and export them as an SRT file."
• "Create subtitles for my YouTube tutorial video and keep each caption line under 42 characters."
• "Transcribe the dialogue in this webm clip and add captions with a reading speed suitable for a general audience."

Getting Connected

Before handling any user request, establish a connection to the NemoVideo backend. Show a brief status like "Connecting...".

If NEMO_TOKEN is in the environment, use it directly and create a session. Otherwise, acquire a free starter token:

• Ensure a client identifier exists at ~/.config/nemovideo/client_id (create one as a UUID if needed)
• POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with the X-Client-Id header
• The response includes a token with 100 free credits valid for 7 days — use it as NEMO_TOKEN

Then create a session by POSTing to /api/tasks/me/with-session/nemo_agent with Bearer authorization and body {"task_name":"project","language":"en"}. The session_id in the response is needed for all following requests.

Tell the user you're ready. Keep the technical details out of the chat.

Turn Any Video Into a Captioned, Accessible Experience

Getting captions onto your videos used to mean hours of manual transcription, awkward timing adjustments, and expensive third-party services. This skill changes that entirely. Upload your video — whether it's a polished YouTube tutorial, a raw interview recording, or a social media clip — and the AI listens, transcribes, and formats captions with accurate timing so every word appears exactly when it's spoken.

Captions aren't just a nice-to-have anymore. They improve watch time, boost SEO discoverability, and make your content accessible to deaf and hard-of-hearing viewers, non-native speakers, and anyone watching without sound. This skill was built with that full picture in mind — not just dumping text on screen, but producing captions that feel natural and readable.

You stay in control throughout. Want captions in a specific language, formatted for a particular platform, or adjusted for reading pace? Just ask. The skill adapts to your content type, your audience, and your workflow — so you spend less time on logistics and more time creating.

Caption Request Routing Logic

Every caption request — whether you're submitting a raw video file, a YouTube URL, or a pre-uploaded asset — gets parsed and routed to the appropriate transcription pipeline based on media type, language detection settings, and subtitle format preference.