Two ways to make your media more discoverable
Google offers two fully-featured video AI products to make your video library more searchable and valuable.
AutoML Video Intelligence
AutoML Video Intelligence has a graphical interface that makes it easy to train your own custom video classification models, even if you don’t have significant machine learning expertise. It’s ideal for projects that require custom labels which aren’t covered by the pre-trained Video Intelligence API.
Video Intelligence API
Video Intelligence API has pre-trained machine learning models that automatically recognize a vast number of objects, places, and actions in stored and streaming video. It’s highly efficient for common use cases and improves over time as new concepts are introduced.
Video Intelligence API demo
Precise video analysis
Video Intelligence API automatically recognizes more than 20,000 objects, places, and actions in stored and streaming video. It also distinguishes scene changes and extracts rich metadata at the video, shot, or frame level. Use in combination with AutoML Video Intelligence to create your own custom entity labels to categorize content.
Simplify media management
Find value in vast archives by making media easily searchable and discoverable. Easily search your video catalog the same way you search text documents. Extract metadata that can be used to index, organize, and search your video content, as well as control and filter content for what’s most relevant.
Easily create intelligent video apps
Gain insights from video in near real time using the Video Intelligence Streaming Video APIs, and trigger events based on objects detected. Build engaging customer experiences with highlight reels, recommendations, interactive videos, and more.
Automate expensive workflows
Reduce time and costs associated with transcribing videos and generating closed captions, as well as flagging and filtering inappropriate content.
Process and store on Google Cloud Platform
Seamlessly integrate with Google Cloud Storage to easily store and upload videos to your model. Select the region where processing will take place and choose from any region where Google Cloud Platform is available. Benefit from a consistent API, low-latency, and speed across multiple storage classes.
Which video product is right for you?
You can work with either one or reap the benefits of both products by using Video Intelligence API to quickly categorize content using thousands of predefined labels and using AutoML Video Intelligence to create additional custom labels to suit your specific needs.
|AutoML Video Intelligence||Video Intelligence API|
Use REST and RPC APIs.
Use a graphical UI
Use a graphical user interface.
|Predefined or custom labeling|
Classify video using predefined labels
Pre-trained models leverage vast libraries of pre-defined labels.
Classify video using custom labels
Train models to classify video via labels you choose.
Detect shot changes
Detect scene changes in a segment or throughout the video.
Detect and track objects
Detect and track objects, how many, where they are within the frame (bounding box), and when they show up (timestamp).
Detect and extract text
Detect and extract text using OCR, know where it is within the frame (bounding box), and when it shows up (timestamp).
Detect explicit content (adult, violent, etc.) within images.
Analyze streaming and stored video
Analyze streaming video and stored video.
Automate video transcription for closed captioning and subtitles
Transcribe speech to text with punctuation. Refine results with alternatives provided for transcribed words or phrases. Censor profanities. Transcribe up to two audio tracks from multitrack video files. Currently supports English.
Google Video Intelligence allows CBS Interactive to plug into our existing video encoding framework to generate video metadata. It provides us with options to use as is or to enhance other models. The performance and reliability allows us to enhance the video experience for our customers and improve content awareness and personalization.Adam Leary, VP, Data Science Services, CBS Interactive
Identify when inappropriate content is being shown in a given video. You can instantly conduct content moderation across petabytes of data and more quickly and efficiently filter your content or user-generated content.
Build a content recommendation engine with labels generated by Video Intelligence API and a user’s viewing history and preferences. This will simplify content discovery for your users and guide them to the most relevant content that they want.
Create an indexed archive of your entire video library by using the metadata from Video Intelligence API. Ideal for mass media companies, Video Intelligence API can automatically analyze content and make the results immediately accessible via the API.
You can identify appropriate locations in videos to insert ads that are contextually relevant to the video content. This can be done by matching the timeframe-specific labels of your video content with the content of your advertisements.
AutoML Video Intelligence pricing
AutoML Video pricing is based on training and prediction. The time required to train your model depends on the size and complexity of your training data. Pay only for the compute hours used. For more detailed pricing information, please view the pricing guide.
|Cloud video classification||40 node hours of free training credit per account (lifetime).||
$2.94 per node hour.
For each unit of time, we use 9 nodes in parallel, where each node is equivalent to a n1-standard-4 machine with an attached NVIDIA® Tesla® V100 GPU.
|Cloud video classification||5 node hours of free prediction credit per account (lifetime).||
$0.42 per node hour.
For each unit of time, we use 1 node equivalent to a n1-standard-8 machine.
AutoML Video Intelligence
Create a custom machine learning model for video detection.
Video Intelligence API
Integrate video detection features within apps, in the coding language of your choice.
Products or features listed on this page are in beta. For more information on our product launch stages, see here.