Overview
VidNavigator’s analysis capabilities allow you to go beyond simple transcription and understand the content of a video at a deeper level. You can get an AI-generated summary, identify key topics and speakers, and even ask specific questions about the video’s content. Every analysis returns atranscript_analysis object with:
summary: an overview of the contentpeople: people mentioned, with the context they appear inplaces: locations referencedkey_subjects: important topics, with a description and importancequery_answer: when you pass aquery, the directanswerplus therelevant_segmentsof the transcript that support it
Prerequisites
- A valid VidNavigator API key.
- The Python or JavaScript SDK, version 2.1.0 (
pip install vidnavigator==2.1.0ornpm install vidnavigator@2.1.0).
Billing
AI analysis consumesanalysis_request units based on context size. One unit covers up to 15,000 total tokens, and longer contexts are billed with ceil(total_tokens / 15000). For example, a video that takes 17,000 total tokens costs 2 analysis_request units.
Pass include_usage=True (Python) or include_usage: true (JavaScript) to receive a usage block with the exact charges and LLM token counts.
Analyzing a Video
query is optional. Without it you still get the summary, people, places and key subjects.
Analyzing an Uploaded File
Files you have uploaded are analyzed the same way, byfile_id:
Next Steps
- Need specific fields rather than a free-form summary? Use structured data extraction.
- See the Analyze Video and Analyze File API references.

