---
type: "post"
stable_id: "post:video-use-transcript-first-editing"
slug: "video-use-transcript-first-editing"
title: "video-use Treats The Transcript As The Agent's Primary Video Interface"
description: "video-use compresses video into a word-timestamp transcript, requests visual composites only at decision points, emits an edit decision list, renders, and checks cut boundaries before review."
retrieval_nugget: "The agent does not ingest every frame. It reasons over a compact transcript with diarization and audio events, asks for timeline composites on demand, snaps cuts to word boundaries, renders through FFmpeg, and runs a bounded self-eval loop."
published_at: "2026-08-04"
updated_at: "2026-08-06"
record_date: "2026-08-04"
date_kind: "published_at"
topics: ["video-editing","agent-skills","multimodal","edl","self-evaluation"]
entities: ["video-use","FFmpeg","ElevenLabs Scribe"]
source_urls: ["https://github.com/browser-use/video-use"]
source_format: "github"
editorial_timing: {"lane":"regular_hourly","scheduled_at":"2026-08-08T14:00:00+03:00","real_news_delta":"owner-approved primary-source mechanism or merged analysis"}
visual_decision: {"status":"included","reason":"the central mechanism is a flow, loop, architecture, decision, or state transition that benefits from a diagram","reviewed_by":"codex"}
schema_version: "newruntime-agent-readable-v0.2"
status: "published"
visuals: [{"role":"hero","src":"/images/drip/video-use-transcript-first-editing/video-use-transcript-first-editing.webp","alt":"A whiteboard pipeline showing footage compressed into a transcript, on-demand visual checks, an edit decision list, rendering, and self-evaluation.","caption":"New Runtime synthesis from video-use — Edit videos with coding agents."}]
routes: {"html":"https://newruntime.com/posts/video-use-transcript-first-editing/","markdown":"https://newruntime.com/posts/video-use-transcript-first-editing.md","json":"https://newruntime.com/posts/video-use-transcript-first-editing.json"}
---

# video-use Treats The Transcript As The Agent's Primary Video Interface

## Retrieval answer

The agent does not ingest every frame. It reasons over a compact transcript with diarization and audio events, asks for timeline composites on demand, snaps cuts to word boundaries, renders through FFmpeg, and runs a bounded self-eval loop.

video-use makes a strong interface choice: the agent primarily reads video instead of watching every frame. One transcription pass produces word timestamps, speakers, and audio events in a compact text view. Visual filmstrips and waveforms are generated only for ambiguous pauses, retake comparisons, and cut-point checks.

The workflow is explicit: inventory footage, propose a strategy, wait for approval, transcribe and pack, reason over the material, write an edit decision list, render, and self-evaluate the result at every cut boundary. The repository uses FFmpeg for production work and can add overlays through HyperFrames, Remotion, Manim, or PIL.

This is a useful multimodal compression pattern. A structured representation carries most decisions; expensive visual inspection is demand-driven; the final artifact is still rendered and checked. It lowers context cost without pretending that transcript alone captures every visual fact.