Currently, content can be added through the duohub app.

API support will be available in the future.

Steps to Add Content

  1. Sign up to the app at app.duohub.ai
  2. Navigate to “Content” in the left sidebar
  3. Click the + button
  4. Select your content type:
    • Webpage
    • Sitemap
    • Video
    • Audio
    • Document
  5. Add your content

Content Types

Webpage

Individual webpages can be quickly added and processed by our system. The content parser automatically removes navigation elements, advertisements, and other distracting elements to focus on the main content. This ensures that only the relevant information is processed and tokenized for your use.

  • Add a single webpage
  • Automatic content parsing
  • Removes header/footer links
  • Focuses on main body content
  • Processing complete when tokens are counted

Sitemap

Sitemaps provide an efficient way to process entire websites at once. Simply provide any website URL, and our system will automatically locate and process the sitemap, converting each page into searchable content. This is particularly useful for large websites or documentation that needs to be processed in bulk.

  • Add entire website content via sitemap
  • Paste any website URL
  • Automatically finds sitemap in common locations
  • Processes all links individually as webpages

Processing Large Sitemaps

Warning: Processing sitemaps with 2000+ pages may experience delays of 30 minutes or more as well as job failures. This is sually because of the presence of 404 links in the sitemap or global rate rate limiting being hit. If your sitemap does not reach “File Ready for Use” status within 30 minutes, please reach out to us.

Audio

Our audio processing system handles various types of audio content, from podcasts to meeting recordings. The system can distinguish between different speakers and process their content separately, making it easier to work with multi-speaker recordings. This is particularly valuable for meetings, interviews, or any content where speaker separation is important.

  • Support for podcasts and recordings
  • Specify number of speakers
  • Multi-speaker content separated by speaker
  • Enables selective speaker content use

Download Podcasts

Currently we do not support downloading podcasts. You will need to download the audio locally before adding it to duohub.

While we cannot officially recommend specific tools for downloading podcasts, here is a general process that some users have reported success with:

  1. Find your podcast on a streaming platform (e.g., Stitcher, Spotify)
  2. Copy the episode URL
  3. Use an online audio converter service, for example audio.online-convert.com
  4. Download the resulting MP3 file

Please ensure you have the right to download and use any podcast content before proceeding.

Video

Video content is processed by extracting and analyzing the audio track, making it possible to work with content from various sources. Whether you’re working with YouTube videos, educational content, or recorded meetings, our system can handle videos of any length. The audio is processed separately to ensure accurate content extraction.

  • Supports YouTube, tutorials, meeting recordings
  • Any length accepted
  • Audio extracted and processed separately

Download from YouTube or Vimeo

Currently we do not support downloading videos from YouTube or Vimeo. You will need to download the video locally before adding it to duohub.

We cannot recommend any specific tools for downloading videos from YouTube or Vimeo. However, some users have reported success using:

Document

Our document processing supports multiple file formats and automatically extracts text while maintaining the document’s structure. This makes it easy to work with various types of documents, from simple text files to complex PDFs, ensuring that all your written content is properly processed and indexed.

  • Supports Word, PDF, and TXT formats
  • Automatic text extraction

Processing Status

Each file displays three white dots indicating:

  1. File Received
  2. File Processed
  3. File Ready for Use

The status should automatically refresh, though you can also manually refresh it.

If a file is stuck at “File Received” after 30 minutes, please reach out to us.