VoCaption offers unparalleled, accurate real-time Speech-to-Text processing across a diverse and expanding language base.

As part of a larger solution provided by Screen, VoCaption empowers you to deliver automatic subtitling across the most comprehensive range of linear, OTT and file based formats in the market today.

Automatic Live Subtitling Speech to Text

Although VoCaption can be used in standalone mode with a third-party subtitling system, its full benefits are felt when used in conjunction with Screen’s market-leading subtitle delivery and workflow platforms. One of the major benefits VoCaption enables within a Polistream system is the ability to automatically switch to an automated subtitling feed in the event a file has not been put to air and then revert back to file playout when that has been re-established. This reduces the volume of fines a broadcaster may incur for loss of subtitling. Inputs into the VoCaption system are achieved via a line-input, an AES feed or directly from the SDI signal. Speech engine support can be achieved by your local VoCaption instance connecting to a Cloud instance or a local Real-Time Virtual Applicance (RTVA). The RTVA itself offers a growing bouquet of languages, with the added benefits of dramatically improving the processing latency and the added security of knowing the entire solution is being provided on a secure, in-house installation.