This explains how to run AI analysis later on videos that you have only uploaded but not yet run AI analysis. Use this method when you want to "register just the video first, then run AI analysis on multiple videos together later" or "I uploaded it without narration, but I want AI to analyze it after all."
For details on what each option changes and how to choose, see AI Processing Options: What Each Item Does and How to Choose.
Videos where AI analysis was already run during upload are outside the scope of this article. If processing failed, see How to Re-run Failed AI Processing. If you want to redo a successful result, see the "Note: When re-running successful processing results" section in that same article.
Steps to run
- Open [Materials List] in the sidebar
- Click on a video that has not yet been analyzed with AI to open the material detail modal
-
Click the [Run AI processing] button displayed at the bottom of the detail modal
- The AI processing options modal opens. Adjust the following as needed:
- Videos without narration (analyzed only by video): Check this for videos without narration, videos with only background music or mechanical sounds, or videos where speech is unclear
- Recognition Language (in [Advanced settings]): The language of the speaker in the video. Setting this correctly improves transcription accuracy
- Video description: Entering what the video is about improves analysis accuracy
- Split granularity: The granularity of step division (Process / Step / Action / Single). "Step" is recommended when publishing as an SOP
- Target step count (in [Advanced settings]): Specify approximately how many steps the entire video should be divided into, or the number of seconds per step. With the default [Auto], AI determines the division based on granularity
- Reference SOP to use (in [Advanced settings] / Beta): Specify an existing SOP file and split according to the divisions in that material (see Specify a reference SOP during video analysis (Beta) for details)
- Text style: The ending of step text (Imperative / Honorific / Suggestive). If you have registered How to write SOPs, you can also select [Follow policy] (default)
- Subtitle style: The ending of action subtitles in the video. This can be set separately from the step text (default is [Imperative]). Select [Match text] if you want to match the step text
- Click [Run], and the status will change to "Waiting" and AI analysis will begin in order
Analysis completes in approximately the same amount of time as the video length. For longer videos, analysis continues even if you close the app, and you will be notified by email when it completes.
Starting from the AI status tag
You can also click the AI status tag in the top right of the material card (such as "Not run" for unanalyzed videos) to reach the same detail modal and AI processing options. This is convenient when you want to add multiple videos to the analysis queue in order from the materials list.
Frequently asked questions
Q. Can I analyze multiple videos at once?
A. You need to press [Run AI processing] → [Run] for each video. After execution, they are added to the queue in order, so you can just open the detail modal for the next video and press the button to process them in a batch.
Q. What if I want to adjust the AI processing results later?
A. Once analysis completes, you can open the detail modal [Check AI analysis results] → [Re-run AI] to change options and re-analyze (processing will be overwritten). See the supplementary section in How to Re-run Failed AI Processing for the procedure.
Q. What if I want to skip AI analysis during Step 1 upload?
A. In the AI processing execution screen during upload, cancel without pressing [Run], and the video will be registered without AI analysis. You can analyze it later using the procedure in this article.