Skip to main content

Video Transcription Demo

Navigate over to the video-transcription playground in our playground to see the video transcription in action.
Developers today need more than just basic speech-to-text—they need to unlock the full potential of long-form video. With vlm-1, you can transcribe hours of video and extract deep, structured insights in a single API call: from scene changes and chapter segmentation to temporal grounding and visual context. This empowers you to build smarter search, content discovery, and analytics tools for podcasts, lectures, interviews, and more—at scale, with minimal effort.

Analyzing Video Content

Let’s look at a video analysis example to see how vlm-1 can be used to extract structured insights from video content. In this example, we’ll use vlm-1 to transcribe and analyze the full 1-hour and 40 minute Google Cloud Next 25 Opening Keynote, generating segmented chapters with start and end timestamps, visual scene descriptions, and corresponding full transcript.
Let’s look at the few lines of code to transcribe the video with vlm-1:

Understanding the Output

Here’s an example of the output in JSON format, for the entire 8 minute video:
Example Video Transcription
Let’s break down the output into its key components:
  • segments : Segmented video content with start and end timestamps
  • segment.start_time : The start time of the segment in seconds (relative to the start of the video)
  • segment.end_time : The end time of the segment in seconds (relative to the start of the video)
  • segment.audio.content : The raw transcription of the spoken content
  • segment.video.content : The visual scene description of the video content
  • metadata.duration : The total duration of the video in seconds
In subsequent guides, we’ll cover more advanced capabilities like topic extraction, entity recognition, and sentiment analysis.

Key Features

  • Temporal Grounding: Precise time segmentation and content localization
  • Visual Analysis: Scene descriptions, object recognition, and text extraction
  • Long-form Support: Process videos up to 4+ hours with automatic segmentation
  • Batch Processing: Efficient handling of large video collections

Try our Video / Audio -> JSON API today

Head over to our Video -> JSON or Audio -> JSON to start building your own video/audio processing pipelines with VLM Run. Sign-up for access on our platform.