Search your videos by a scene description, a line of dialogue, or a named person. FrameQuery returns matching timecodes across your indexed library on Windows and macOS.
Paid indexing. Free local search, including offline.
3 results · 12ms
A001_C003.mov
VisualB_ROLL_LAKE.mp4
TranscriptINTERVIEW_EXT.mov
ObjectWorks with
your workflow.
Exports to your NLE. Reads cinema RAW natively.
Search can cover your whole library or a selected project. Open a result to review the matching timecode.
Describe the shot you remember, such as “sunset over water.” Visual search checks the frames and scene descriptions in your indexed footage, including clips with no dialogue.
Put remembered words in quotes, or use semantic search to describe the topic in plain language.
To find a person across shoots, name them in the People tab and use an @ filter.
Also filter by time range, dominant color, match type (transcript, object, scene), date range, source folder, project, or named index. Combine any of these with free-text search.
Filter by person, face or voice. Use @"full name" for multi-word names.
Exact phrase match. Finds the precise moment someone said this.
Exclude a term. Combine with other queries to narrow results.
Metadata filters: codec, resolution, camera, FPS, ISO, lens, and more.
A quoted phrase searches for those words. Semantic search compares meaning across transcripts, scene descriptions, detected objects, and analyzed video frames. Try “talking about a road trip” for dialogue about travel, or “quiet morning light” for the look of a scene. Review the matches and narrow the scope to a project or person when needed.
FrameQuery combines a Tantivy keyword index using BM25 relevance scoring with semantic matches. How semantic video search works.
The indexes and query processing stay on your machine, and the search index works offline. Keep the source drive connected to play or export footage.
Import footage from your drives. FrameQuery extracts sampled frames and audio for cloud analysis, then stores the search results locally. Your originals stay on your drives. Extracted data is discarded after processing. See how video indexing works.
Select
Files or folders, local or cloud
Extract
Frames and audio on-device
Analyse
Scenes, objects, speech, faces
Index
Stored locally and searchable
Select
Files or folders, local or cloud
Extract
Frames and audio on-device
Analyse
Scenes, objects, speech, faces
Index
Stored locally and searchable
Paid plans include hours of video each month. Hours count the duration of your footage. Processing time depends on the footage, your device, and your connection.
Free
Free
Search only, no indexing
Starter
$19/mo
10 hrs of video/mo
Pro
$45/mo
50 hrs of video/mo
Max
$190/mo
300 hrs of video/mo
Larger archive? Book a call and we will bulk-process it.
Video and audio are analysed in parallel. Scene detection, object recognition, and speech-to-text with speaker separation run at the same time on every clip.
Detected objects such as people, vehicles, animals, and props become searchable metadata. Search for “red car” or “laptop” and review matching moments.
Learn about visual searchNatural-language summaries of each scene including setting, action, mood, and composition. Also extracts shot type (wide, close-up, medium), shot angle, and dominant color. Search by how a shot looks.
Learn about scene detectionFull speech-to-text with word-level timestamps and automatic speaker diarization. Each segment is tagged with a speaker. Search by who said something.
Learn about transcription searchNo transcoding step. Point FrameQuery at your media as-is. Professional camera RAW formats use native SDKs with GPU acceleration; everything else goes through FFmpeg. RAW format details · Full compatibility list
Assign matching faces and voices to a person, then search their footage by name. Voice cards show the source clip and a waveform you can scrub before assigning.
Sarah
3 faces · 1 voice
James
5 faces · 2 voices
Right-click or drag onto a person to assign
Voices 2
Interactive illustration · no audio0:42–0:47
0:00 / 0:05
1:18–1:23
0:00 / 0:05
A voice you can check before you name it.
Drag a waveform or try Assign with the example person, Sarah Chen.
All biometric data processed and stored on-device only
Recognition runs on your machine on footage you’ve already analysed. Biometric embeddings and labels are excluded from shared indexes.
Recognition is optional and consent-gated, and adds no extra cost.
FrameQuery backfills any videos already in your library when you turn it on.
Export search results or selections as timeline-ready files for Final Cut Pro, Premiere Pro, DaVinci Resolve, Avid, and more. Free on every plan. Learn about NLE export.
What you can search, what leaves your machine, and what indexing costs.
Search every word spoken across your video library.
Learn moreFind anyone by face or voice across your footage.
Learn moreDescribe what you need in plain language.
Learn moreFCPXML, Premiere XML, EDL, LosslessCut.
Learn moreTimecode and waveform matching for dual-system audio.
Learn moreScene boundaries, take organization, and grouping.
Learn moreR3D, BRAW, and ProRes RAW with native SDKs.
Learn moreTimecoded comments, annotations, and approvals.
Learn moreShare indexes and back up to local, Drive, or NAS.
Learn moreFind where a frame or clip came from on the web, or every near-duplicate in your own library.
Learn moreSend a video, get back scenes, detections and a diarised transcript for your own product.
Learn moreFrameQuery returns matching timecodes across your indexed library on Windows and macOS.
Paid indexing. Free local search, including offline.
