Filler clean
- Category: Middleware
What it is
Cleans filler words, punctuation and similar from word-level subtitles, then hands them to rough cut or sensitive-word detection.
This node grew out of the related Lab tools: wires in a blueprint replace the step-by-step clicks in the Lab, which makes it easy to reuse and to hand to an agent.
Related Lab tools
Inputs
| Name | Description |
|---|---|
| Word-level subtitles | Word-level subtitles with timestamps |
| Extra sensitive-word list | Connect to the matching input of this node |
Outputs
| Name | Description |
|---|---|
| Word-level subtitles | Word-level subtitles with timestamps |
How to connect
Word-level subtitles go in and come out. Connect the cleaned result to rough cut or sensitive-word detection, not straight to a subtitle import.
Settings
| Name | Description |
|---|---|
| Filler words | Set in the node panel |
| Punctuation | Set in the node panel |
| Sensitive words | Set in the node panel |
| Replacement rules | Set in the node panel |
Typical downstream
Smart cut rules, Detect audio sensitive words
Notes
- Before writing back to the editing app, make sure LmBox is connected to the matching app (DaVinci Resolve / Premiere / After Effects and so on).
- The result is still word-level. Connect it to rough cut or sensitive-word detection; use sentence-level subtitles to import subtitles.
Related recipes
- Recognize speech, rough cut and place: see the recipes in the Blueprint lab overview
Agents / MCP
For agents or developers (optional)
- Once LmBox's open MCP is connected, the full ports and settings can be read from the catalog. This page is written for people, not around machine fields.
- Node type:
filler-clean
← Back to the Blueprint lab overview · Lab features overview · Blueprint lab guide