The Problem
Most tools give you a transcript for a single file. FrameQuery gives you searchable, timestamped, speaker-identified transcripts across your entire library.
How It Works
Every word is timestamped. Jump to the exact moment a phrase was spoken, not just the general area.
Automatic speaker detection identifies who said what. No manual labelling required.
Name your speakers and search with @syntax. '@Sarah quarterly targets' finds only Sarah's comments on that topic.
Wrap phrases in quotes for exact matches. Search '"budget approval"' to find those exact words in sequence.
Beyond Words
Dialogue tells you what was said. Object detection, scene descriptions, and face recognition tell you what was happening. Combined, they give you complete context.
See what was in frame when something was said. Find 'product mention' clips where the product is actually visible.
Understand the visual context. Was it an interview setup, a presentation, or a casual conversation?
Know who is on screen, not just who is speaking. Match voices to faces across your library.
Export
Export transcript search results directly to your NLE. Each result includes the timecode range, so clips land on your timeline at the right moment.
EDL and FCPXML import for timelines and color workflows.
Premiere XML export for seamless bin integration.
Native FCPXML support. Open results as a new event.
Pricing
Every plan includes the full feature set.
Free
Free
Search only
Starter
$19/mo
10 hrs processing
Pro
$54/mo
50 hrs processing
Max
$228/mo
300 hrs processing
FAQ
Yes. Automatic speaker diarization detects distinct speakers and labels each transcript segment. You can name speakers for @mention search.
Yes. Wrap any phrase in quotes to find exact matches. Search '"annual review"' to find those exact words in sequence.
Yes. Transcripts are stored in your local search index. Searching happens entirely on your device.
Transcript search covers spoken content. For videos without dialogue, scene descriptions and object detection make the visual content searchable.
Transcription quality depends on audio clarity. Clean audio from dedicated microphones produces highly accurate results. Noisy environments or distant audio may reduce accuracy.