VOX Load

VOX Load, our tool that optimizes the production of audio description, closed captioning, transcription, translations, and subtitling.

Since 2019, we have been studying how intelligence tools can support accessibility production processes.

Real-time closed captions, with high quality to help you meet your deadlines.

Our technology generates captions in real time using speech recognition, a breakthrough for TV stations, live events and streaming.

Key Features:

You don't need a server, and you can use the encoder or playout system you already have;

Ability to connect up to 10 simultaneous streams on the same account;

Automatic speaker switching detection;

A dictionary of words and names for easy recognition;

Accuracy of up to 99%;

Cloud-based tool;

Option to schedule appointments and hire on an hourly basis;

Simultaneous translation may be available.

Using our tool, you can design the captions:

Large screens, displays, and LEDs via HDMI;

On its online platform;

Users can access it directly from their cell phones by scanning a QR code, without having to download any apps.

The platform can be contracted without the service, which means that operations can be managed directly by the client’s team using a username and password.

VOX LOAD is online and can be managed from anywhere (if necessary, we can restrict the license and users to specific IP addresses).

We have technical support to address any technical issues, but this does not include system operation.

The platform operation service can be contracted separately for management and operation with the MAV team.

Some live programs (reality shows or those with many overlapping voices) do not perform well with speech recognition; in such cases, it is possible to hire stenography services separately.

What is VOX Load like in practice?

Transcription and Translation

To transcribe, we upload the video and/or audio onto the platform,

This allows the transcription to be done automatically.

Next, you can download the text file with the transcript or, automatically translate it into up to 45 languages.

Closed Caption

LIVE 

  • Our tool offers closed captions and real-time subtitles.
  • Our technology generates real-time captions using speech recognition, representing a major advancement for TV broadcasters, live events, and streaming services.
  • You don't need a server, and you can use the encoder or playout system you already have (for TV stations).
  • You can connect up to 10 simultaneous streams on the same account.
  • We have a 95% accuracy rate for transcription.
  • Automatic speaker change detection.

 

PRE-RECORDED

  • Just upload the audio or video to the tool.
  • VOX Load transcribes and keeps track of the time.
  • The material is available for review and editing directly on the platform.
  • A text file with the extension of your choice.
  • Ability to automatically translate content into up to 45 languages.

Audio Description

For audio description, we upload the script to the platform in .srt format, including the timecodes for synchronization (you can create the script directly within the platform).

This allows the descriptions to be automatically aligned.

Next, we can choose the neural voice, adjust the pitch and speed, and add other descriptions as needed.

Finally, just download the audio file with all the descriptions synchronized.