Workflows
AI Video Search Without Uploading Your Footage to the Cloud
Most AI video search tools require uploading your originals. FrameQuery keeps your footage local, extracts only frames and audio on your device for cloud analysis, and runs all biometric processing on-device.
Making footage searchable with AI usually means uploading it. For 8 TB of raw cinema files that is impractical, and for footage with identifiable people it means a cloud service running face recognition and storing the biometric data.
Many professionals skip AI video tools for that reason and scrub manually instead.
FrameQuery processes locally where privacy matters and uses cloud compute only for analysis that does not need the original files.
Why most AI video search tools require uploads
AI video analysis is computationally expensive. Running speech-to-text, object detection, and scene description models requires GPUs that most workstations do not have (or cannot dedicate to indexing while other work is happening). Cloud processing solves the compute problem.
The simplest architecture is to upload the original video file, process it on cloud GPUs, and return the results. Most AI video tools work this way. It creates several problems:
Transfer time and bandwidth. Uploading terabytes of raw footage takes days even on fast connections. For facilities without high-speed upload bandwidth, it is impractical.
Storage costs. Cloud storage for raw video is expensive. R3D, BRAW, and ProRes files are large, and keeping them on remote servers adds ongoing cost.
Data exposure. Your footage now exists on someone else's infrastructure. For client work under NDA, legal proceedings, unreleased commercial content, or any footage involving identifiable individuals, this creates liability.
Vendor lock-in. If the service shuts down, changes pricing, or has a breach, your footage and metadata are entangled with their platform.
FrameQuery's approach: frames and audio only
FrameQuery separates compute from data.
Local extraction. Before any cloud call, FrameQuery reads your footage on your device and extracts just what the analysis models need: sampled keyframes and the audio track. The rest of the file (container wrappers, unused colour channels, high-bitrate pixel data between keyframes, alternate streams) never leaves your machine. No full-quality proxy is generated, uploaded, or stored.
Cloud processing of extracted data only. The frames and audio are sent to cloud GPUs for transcription, object detection, and scene description. Your original R3D, BRAW, ProRes, or MXF files never leave your machine and are never stored on FrameQuery's servers. The extracted data is discarded the moment analysis completes.
Results returned as metadata. The cloud sends back structured data: timestamped transcripts, object labels, scene descriptions. This metadata is a few kilobytes per clip and contains no video content.
Local index storage. The returned metadata is stored in a local Tantivy search index on your machine. Searching happens entirely on-device with no network calls.
You get GPU-accelerated analysis without uploading your originals.
Biometric processing stays on-device
Face and voice recognition require special handling because they produce biometric data. A face embedding is a mathematical representation of someone's face. A voice print captures the acoustic characteristics of someone's speech. Both are sensitive data categories under privacy law.
FrameQuery runs all face and voice recognition processing 100% on your local machine. No face data, no voice prints, and no biometric embeddings are sent to the cloud. The models run on your CPU and GPU, and the resulting data stays in your local search index.
When you share or export an index, biometric data is never included. Face embeddings, voice embeddings, and person labels are automatically stripped. Only non-biometric metadata (descriptions, transcripts, tags, timestamps) travels with the shared index. If a recipient has access to the underlying footage, they can run their own recognition locally and assign their own labels.
Biometric data has legal implications that general video metadata does not.
Local processing in specific industries
Legal and litigation. Video depositions, surveillance footage, and recorded evidence have chain-of-custody requirements. Cloud uploads create exposure of privileged content. Local processing preserves evidentiary integrity.
Corporate communications. Internal meeting recordings and HR documentation contain sensitive business information. AI search is valuable only if the content remains within the organization's infrastructure.
Documentary filmmaking. Documentary footage often includes vulnerable subjects or whistleblowers who consented to be filmed but not to have their images uploaded to a cloud platform. Local biometric processing respects those consent boundaries.
Broadcast news. Footage involving sources, unpublished investigations, and sensitive locations carries competitive and legal risk, and many newsrooms avoid cloud-based AI tools for that reason.
BIPA, GDPR, and biometric privacy law
Biometric privacy regulation is expanding. Illinois' Biometric Information Privacy Act (BIPA) requires informed consent before collecting biometric identifiers and imposes strict requirements on storage and sharing. GDPR classifies biometric data as a special category requiring explicit consent and data protection impact assessments.
For any organization processing video that contains identifiable faces, where biometric analysis happens is a compliance consideration.
On-device biometric processing simplifies compliance. If face embeddings are generated and stored locally, they are not transmitted to or processed by a third party. The organization retains full control over the biometric data and can delete it without coordinating with a vendor.
Organizations still need internal policies for handling biometric data, but there is no third-party data sharing to account for.
The trade-offs of local-first architecture
Biometric processing on your machine uses your CPU and GPU and may be slower than dedicated cloud hardware. Cloud-indexed modalities require an internet connection during indexing (searching is offline afterward). The local extraction step adds a few minutes compared to a direct-upload pipeline.
What stays local, what goes to the cloud
| Component | Location | |---|---| | Original video files | Your machine (never uploaded) | | Frames and audio for analysis | Extracted on your machine, sent to the cloud, then discarded | | Transcription processing | Cloud | | Object detection processing | Cloud | | Scene description processing | Cloud | | Face recognition processing | Your machine | | Voice recognition processing | Your machine | | Search index | Your machine | | All search queries | Your machine (no network calls) |
Queries, face identification and search results are all generated locally from your own index. The cloud is involved once, during indexing, and only with the frames and audio required for analysis.
Download FrameQuery to try AI video search that keeps your footage local.