Remote interpreting

Remote and AI-assisted simultaneous interpreting for hybrid events


A hybrid event is a combination of face-to-face and online components that allows speakers, delegates and interpreters to participate at the event onsite and remotely. Saving space, reducing travel and logistics costs, reducing CO2 emissions and having access to our large network of professional interpreters worldwide are just some of the benefits of this solution.

While the technicians are on site and the listeners are in their offices at home or elsewhere in the world, the interpreters work as usual in the interpreting booth – either on site or in a hub provided by the technology provider. In such scenarios, both the video and audio transmission from the conference venue and the team organisation need to work flawlessly. Choosing a reliable partner who can provide comprehensive support is essential to the success of such events.

Possible scenarios for remote simultaneous interpreting

The following scenarios are common with Remote Simultaneous Interpreting (RSI):

1. On-site event with remote interpreters and participants

  • The venue is not large enough to accommodate all participants and interpreting booths. Remote and on-site participants listen to the interpretation via an app. The interpreters are monitored throughout the event.
  • We manage the interpreting logistics for the event with the help of our partner companies. The conference is streamed to a platform, the interpreters receive the audio and video streams live and work remotely. The internet connection and the interpreters are monitored throughout the event.

2. On-site event with participants on site and remote interpreters

  • Remote interpreters are connected to the conference and their interpretation is transmitted to the participants on site.
  • Onsite participants listen to the interpretation via an app or using receivers.

3. On-site event with interpreting booths and on-site as well as remote participants

  • The interpreters work in booths and their interpretation is transmitted online.
  • Participants on site use infrared or FM audio receivers, while those in other locations listen to the interpretation via a platform on their preferred devices.

Remote simultaneous interpreting via mobile app

Remote simultaneous interpreting via app allows users to access interpreting services conveniently from their smartphone. The technical requirements are relatively simple: a stable internet connection and a compatible smartphone are all that is needed.

However, app-based remote interpreting does have its challenges. As with any technology-based solution, there is a risk of connection problems, audio dropouts or other technical issues. In addition, non-verbal signals such as gestures or body language cannot be fully conveyed, which can lead to misunderstandings or poorer interpreting quality.

Another important detail is often overlooked: Participants need to make sure that their mobile devices are sufficiently charged during longer events. Otherwise, they run the risk of missing the interpretation if the battery runs out 😊.

Here are some of the requirements that need to be met:

  1. Hardware

A powerful laptop computer is required. A capture card with HDMI or SDI input is also required to convert video and audio from cameras, consoles or other video sources into a digital format that can be recorded or streamed to a computer.

The camera feed can come from a vision switcher or directly from a standalone camera. It is also recommended to use a special 46-fallback router that can manage both IPv4 and IPv6 addresses and automatically switch between these protocols in case of problems.

  1. Connectivity

For connectivity, a 3.5Mbps Ethernet connection is required to ensure video and audio upload, with a dedicated connection recommended. In addition, a speed of 0.5Mbps per listener connected to the venue’s Wi-Fi should be included. It is important to have an XLR audio feed from the audio mixer. The video feed should be provided via SDI or HDMI connections from the camera mixer, or directly from a camera pointed at the stage.

A simple Wi-Fi connection is not sufficient.

AI-supported simultaneous interpreting

For hybrid events, we offer AI solutions such as speech-to-text software. These tools are becoming increasingly popular and are ideal for events where reproducing spoken content is the main objective and minor inaccuracies are acceptable. However, they are not suitable for events that require precise language and nuanced communication, as speech recognition accuracy can vary and non-verbal cues are minimally captured.

We see the use of such solutions more as a complement to the proven services of professional simultaneous interpreters, particularly in the following cases:

  • To make the event more inclusive by providing captioning for participants with hearing impairments or disabilities.
  • To make participants more comfortable by providing them with additional interpretation in the form of subtitles. It is known that some people, even if they understand the language, prefer to have a written version of what is being said in order to understand it better.

Find out more about our AI-assisted simultaneous interpreting on our remote interpreting page.