Momen Hosts Live Workshop on Building Video-to-Text Apps With Gemini 2.5.

Momen announced on LinkedIn that it will host a live workshop on June 6 at 6 PM PT showing how to build AI applications that process video using Google Gemini 2.5's multimodal capabilities. The session, scheduled on Luma, will walk through creating a no-code tool that automatically summarizes video content and extracts key timestamps.

The workshop targets non-technical founders and builders who want to leverage video understanding without writing code. Momen positions the session as a practical demonstration of combining Gemini 2.5's video processing with its own no-code platform to "turn any video into structured, useful content."

Google's Gemini 2.5 model introduced native video understanding capabilities, allowing the AI to process visual and audio information from video files directly. Momen's workshop will demonstrate how to build applications that use these capabilities through a visual interface, removing the need for developers to write API integration code or handle video preprocessing.

Attendees will learn how to generate structured summaries with timestamps, a feature particularly relevant for content creators, educators, and teams managing video libraries. The platform handles the connection between user uploads, the Gemini API, and output formatting through pre-built components.

Momen has been steadily expanding its AI integration features. The platform recently added support for Nano Banana Pro image generation and released cloneable workflows for automated image descriptions using GPT-4o-mini.

The June 6 session will be streamed on YouTube, with registration available through Luma. Momen has been hosting regular livestreams demonstrating specific use cases and technical implementations on its platform. Past sessions are archived on the company's YouTube channel.

The workshop follows Momen's pattern of releasing cloneable templates and workflows that users can duplicate and customize for their own needs. This approach lets builders start with working examples rather than building integrations from scratch.

For teams already managing video content manually, the workshop offers a practical entry point into automated video processing. The focus on timestamps and structured summaries suggests applications in meeting transcription, course content, and media asset management. The no-code approach removes technical barriers but still requires understanding how to structure prompts and design user workflows within the platform.

Momen's registration page notes that no coding is required but does not specify whether attendees need existing Gemini API access or if the platform provides integrated access to the model.