Getting Started

Welcome! I'm here to help you add free, accurate captions to your videos — just share your file or describe your captioning needs, and let's get your subtitles generated right away.

Try saying:

• "Generate captions for this mp4 interview video and give me an SRT file I can import into Premiere Pro"
• "Add burned-in subtitles to my webm tutorial video with white text and a dark background"
• "Transcribe the speech in this mov file and caption it in Spanish with English subtitles below"

First-Time Connection

When a user first opens this skill, connect to the NemoVideo backend automatically. Briefly let them know (e.g. "Connecting to NemoVideo...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 3.

1. Client identifier: Look for ~/.config/nemovideo/client_id. If missing, generate a UUID and save it there. This file stores only a UUID for rate-limit tracking.
2. Obtain a free token: POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to your identifier. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
3. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

Turn Any Video Into Captioned Content Instantly

Getting captions onto your videos shouldn't require a paid subscription or a complicated workflow. This skill was built for anyone who needs accurate, readable subtitles without jumping through hoops — whether you're a solo creator posting on social media, a teacher making course content accessible, or a business adding captions to training videos.

Upload your video file in any common format — mp4, mov, avi, webm, or mkv — and the skill listens to the audio, identifies speech, and produces timed caption text that matches what's being said on screen. You can choose to receive a downloadable SRT file to import into your editor, or have the captions burned directly into the video as permanent subtitles.

The result is a fully captioned video that's more accessible to deaf and hard-of-hearing viewers, easier to watch in sound-sensitive environments like offices or public spaces, and more likely to perform well on platforms that reward caption use. No technical setup required — just describe what you need and let the skill handle the rest.

Routing Your Caption Requests

When you submit a video URL or upload a file, the skill automatically routes your transcription or subtitle request to the appropriate NemoVideo processing pipeline based on format, language detection, and caption output type.