Video Indexing Platform

Yactraq Speech2Topics is a cloud-based video indexing platform. We use speech recognition & NLP (natural language processing) to auto-generate time-coded topics.


Yactraq topics are analyzed for frequency, relevance and other proprietary metrics to develop deep & rich metadata on any kind of digital audio or video content. This metadata can then be applied to:

1. Usability (Search, Discovery, Navigation)

2. SEO

3. Contextual advertising: Yactraq has developed an app called Speech2Ads on top of the Speech2Topics platform. We currently offer a turnkey solution, delivering CPC text ads in partnership with Adknowledge, Yahoo/, Looksmart, 7Search, and others.

4. Productivity (Video Editing)

5. Digital Asset Management / Content Management



Customers can pay Yactraq either:

1. A revenue share on ad/subscription revenues derived from free topics, or
2. A software service/license fee per minute of video processed

Please contact or 1 888 955 0552 for a custom quote.


Our Low-cost, high accuracy Speech2Topics technology can process live or stored streams (audio or video) that contain speech data and produce a time-coded set of topics. These topics are taken from a “topic set” that currently features a wide range of 5000 - 10000 consumer-oriented terms. Topics are returned in real time, with a user-defined frequency (e.g. once every 30 seconds) and short lag time. For stored streams, the topics returned are coded to the elapsed playtime of the stream and can thus be indexed against user playback. Topic accuracy can range from 90-100% with low-background noise signals and typical North American accents.

Our topic sets and tailored speech recognition models manage ambiguities well in most cases, with interpretation focused on topic-related speech. As regards distinguishing a tennis court from a food court from a court of law, our topic engine does provide for such disambiguation generally, but for higher accuracy we may need to customize topic sets based on customer requirements. Topics not included in a customer’s topic set are not recognized (e.g. there is a default “adult” filter in place since we do not currently provide an “adult materials” topic set).

As an example, the customer might have a set of video files that will be web streamed. Using Yactraq’s Speech2Topics, each file is pre-processed to produce a JSON-encoded map of the topics covered in the video. This JSON can then be included in the HTML page that embeds the video and keyed to the file’s playback. Using the Speech2Ads service we can then deliver topic-specific, location-aware ad content directly to the user’s web page or mobile viewing platform.

For very high volume/performance requirements we can optionally provide a Linux executable that will process the speech embedded in media files or streams to be run on the customer’s servers. This executable engages with the Speech2Topics and Speech2Ads services via a web services interface. In the future, we plan to allow our customers to choose from a set of predefined topic categories and even to customize their own topic set.

Installation Guide

Yactraq provides a service called Speech2Topics that associates topic information with online
media sources. This is achieved by a combination of speech recognition and natural language
processing on the media’s audio stream to produce a time-indexed “topic stream” for that media
object. Yactraq’s Speech2Ads service can then use this topic stream to drive contextual advertising
delivery to the user’s browser when the media is being played.
In order to use Yactraq’s services, a publisher with Kaltura-managed media must first request a
free consultation at or sign up at
Once this is done and a service contract has been signed, then the service integration can
be initiated. At this point, Yactraq will provide the publisher with a Kaltura/Yactraq integration guide.
This service integration is achieved with the addition of two Javascript files to each page
delivering Kaltura media content, reservation of an area within which Yactraq’s advertising can be
displayed, and then a small Javascript shim establishing the publisher’s identity and options for
choosing and displaying advertising content. No modification is made to the Kaltura player
(publisher-specific themes and templates are never interfered with) and very limited JavaScript skills
are required to complete this integration. With this in place, a publisher can be up and running,
delivering contextual advertising to their users and monetizing their content within hours.

Application Specifications

(Click on the terms to find similiar applications)

Kaltura Edition:

 , ,

Kaltura version:


Kaltura API version:


Prerequisites & Requirements

At this point our system is limited to processing north american accented english speech only.

Support Options

Support Email:

Support Details

Developer Resources

Source Code License

Source Code Repository

Additional notes from the application creator

Application Provider Logo

Provider Details


Yactraq Online Inc.




About the application provider

Yactraq is a platform that enhances the revenue and metadata of online video. We offer video/audio publishers a compelling user & revenue growth opportunity. Our platform does this by generating deep & rich metadata using speech recognition & natural language processing to index online video. Yactraq can help: 1. Monetize video content through contextually targeted ads. 2. Drive traffic by making video content indexable by search engines. 3. Encourage consumers to spend more time on a website through features like accurate search results, content discovery & navigation.

Application Resources

Back to top