Sighthound AI

Sighthound AI offers computer vision products for vehicle recognition, media redaction, and edge AI hardware. Retriever reads license plates and identifies a vehicle’s make, model, color, and generation from live camera streams or uploaded footage. It installs on customer machines through Docker Compose, runs in a browser, and works offline without a required cloud connection. Sighthound says it does not provide vehicle owner or location information. Retriever works with almost any IP camera, though the company recommends specialized LPR cameras for fast-moving vehicles. Redactor detects and redacts video, image, and audio content, and can create searchable transcripts for keyword redaction in 8+ languages. It offers REST API access, batch jobs, webhooks, and a brandable embedded editor. Sighthound says Redactor keeps media files from being sent externally and supports local, on-premise, and private cloud deployments. The company describes Redactor as built for GDPR, CCPA, FOIA, HIPAA, and other global privacy regulations. Pricing includes a free plan, Pro at $2,500 a year, and Server at $3,500 a year; Enterprise pricing is custom.

Sighthound’s offerings cover vehicle recognition and media redaction, with different deployment options for each product. Consider Retriever’s information limits and the listed pricing tiers when evaluating fit.

Retriever may suit teams working in parking, enforcement, law enforcement, tolls and traffic, fleets, logistics, retail, or automotive. Redactor may fit workflows that need media redaction, searchable transcripts, or local and private deployments.

Sighthound AI is a computer-vision suite for teams working with vehicle footage or sensitive media. Its best fit is an organization that needs local processing for recognition or redaction; choose between its distinct products by workflow, not by the breadth of the suite.

Overview

Sighthound pairs Retriever, for identifying vehicles in camera footage, with Redactor, for finding and removing sensitive content from media. It also offers edge AI hardware. The products address separate jobs: Retriever identifies vehicle attributes but does not provide owner or location information, while Redactor supports privacy-focused media handling.

Key features

Retriever vehicle recognition

Retriever reads license plates and identifies a vehicle’s make, model, color, and generation from live camera streams or uploaded footage. It installs on customer machines through Docker Compose, runs in a browser, and works offline without a required cloud connection. That local operation suits sites that cannot rely on cloud connectivity, though its identification stops short of ownership or location data.

Retriever works with almost any IP camera, but Sighthound recommends specialized LPR cameras for fast-moving vehicles. That is a meaningful qualification for toll, traffic, or enforcement use: camera choice can affect whether a general installation is appropriate. Installation guidance is available through the Developer Portal and Knowledge Base, with direct contact as another support route.

Redactor media workflows

Redactor automatically detects and redacts video, image, and audio content. Searchable transcripts help locate keywords for redaction in 8+ languages, while REST API access, batch jobs, webhooks, and a brandable embedded editor support integration into larger workflows. This breadth is useful for teams processing media at scale, rather than occasional manual edits.

Sighthound says Redactor keeps media files from being sent externally and supports local, on-premise, and private cloud deployments. It also says the product is built for GDPR, CCPA, FOIA, HIPAA, and other global privacy regulations. Those are relevant commitments for regulated or disclosure workflows, but they do not remove the need for an organization to assess its own compliance obligations.

Pricing

Sighthound has a free plan and paid annual plans for Redactor. The free tier costs nothing and allows one user, 24-hour access, and up to 2 minutes of video, hosted by Sighthound. It is useful for a small evaluation, but the short video cap and hosted deployment make it a poor fit for sustained or sensitive-media production.

Pro costs $2,500 a year, billed $2,500 /year. It includes one user, unlimited video length, desktop installation, and email support. It suits a single user who needs longer media processing without server deployment. Server costs $3,500 a year, billed $3,500 /year; it starts with one user, with additional users up to five at $500/yr/user. Server deployment, email support, and product training make it the stronger fit for a small team operating a shared installation.

Enterprise has custom pricing and includes one or more users, API access, dedicated private Slack, and private deployment or OEM. It is the relevant tier for organizations needing those integration or deployment options, but carries no published fixed price.

Platforms

Sighthound lists Android, iOS, Linux, macOS, Windows, web, API, and self-hosted support, alongside hybrid deployment options. Retriever’s customer-machine installation and offline operation are particularly relevant to self-hosted deployments; Redactor supports local, on-premise, and private cloud use.

Who it's for

Sighthound describes Retriever use cases across parking, enforcement, law enforcement, tolls and traffic, fleets, logistics, retail, and automotive. It fits organizations that need vehicle attributes from camera footage, provided they do not expect owner or location lookup. Redactor is aimed at teams that need to redact media and search transcripts while keeping files in controlled environments.

Pros and cons

Pros

• Retriever works offline and on customer machines, reducing dependence on a cloud connection.
• Redactor combines audio, image, and video redaction with searchable transcripts and workflow integrations.
• Redactor supports local, on-premise, and private cloud deployments for controlled media handling.

Cons

• Retriever does not return vehicle owner or location information, limiting it to vehicle identification.
• Fast-moving vehicles may call for specialized LPR cameras rather than a general IP camera.
• The free Redactor plan is limited to one user and 2 minutes of video, while Pro is also restricted to one user.
• Sighthound Video is open source but no longer receives active feature development or regular updates; support is best effort for critical issues.

Alternatives

For image-recognition options beyond this suite, browse AI Image Recognition Software.

Choose Face++ if a freemium API with free access and a single API key better fits an API-focused workflow. MediaPipe is a free alternative for on-device ML solutions and framework use. PaddleOCR is a free option for Android and iOS, with an official API free tier capped at 20,000 document pages daily.

Roboflow may suit teams that want a freemium platform with 10 monthly free credits, enough to train about 30 models or run 80,000 inferences. Seeing AI is a free app alternative. SentiSight.ai is worth considering for teams seeking an offline model license with a custom quote and a 30-day free trial. ViSenze offers a 30-day trial for multi-search and AI recommendations. OpenCV is another free alternative.

Verdict

Sighthound is a strong candidate for organizations that need local vehicle recognition or privacy-oriented media redaction, with Redactor particularly compelling when integrations and controlled deployment matter. Choose it for those specialized workflows; look elsewhere if you need vehicle ownership or location data, or if Redactor’s user limits and annual costs do not fit your operation.