Technical specification · Live event production

Professional translation routing, ready for the room.

Interpreter24 is an installable macOS and Windows application for multichannel audio workflows, real-time diagnostics, translation, and local recording. A browser version is also available for convenient access.

System requirements

PlatformMinimum configurationRecommended memory
WindowsWindows 11 · 64-bit Intel or AMD processor · 8 GB RAM16 GB RAM
macOSmacOS 26 · Apple Silicon M1 or later · 8 GB RAM
Intel Macs are not supported.
16 GB RAM

Audio routing and delivery

Multichannel output

Receive translated languages as separate channels in a single audio stream. Map each channel to a physical multichannel audio interface for distribution to language receivers, and change channel mappings at any time.

Multichannel input and passthrough

Bring multiple audio channels into the app and pass selected channels through unchanged. Combine a human interpreter feed with AI translated channels in one production workflow.

Broadcast modes

  • Cloud: participants scan a QR code to access translated audio and captions on their phones.
  • Local USB: route multichannel audio to physical sound cards and receiver systems.
  • Combined: deliver to mobile devices and connected audio hardware together.

Real-time diagnostics

Monitor the session in real time from the operator application while managing the event’s audio and language delivery.

Translation and session setup

AI translation

  • 99+ languages
  • Automatic language detection, including when speakers switch languages
  • Speaker identification
  • Natural synthesized voices
  • Reasoning mode available with supported models

Glossaries and event context

Add words and names to improve recognition and transcription, then define multilingual term translations. Describe the event or provide preparation material such as PDFs; the app can extract people, places, and product names to help tailor translation. Session data can be reused and imported or exported as Excel files.

AI model profiles

FASTAverage word-to-word latency about 2 seconds; natural voices; no customisation.
STANDARDAverage word-to-word latency about 6 seconds.
INTELLIGENTAverage word-to-word latency about 4 seconds; reasoning mode to improve translation.

Latency is an average and can vary with language pair, audio, and operating conditions. Customisation availability depends on the underlying AI model.

Participant receiver

Set the receiver’s app icon and add a custom information page for schedules, links, announcements, or sponsor content. Phone users can choose their language and light or dark theme; captions can identify speakers.

Captions and display

Mobile captions and Caption Wall

Show multilingual captions on participant phones or project them with Caption Wall. Configure text size and colours, show up to two languages side by side, or use a transparent background as an overlay in broadcast software such as OBS.

Recording and session files

Local recording

Record multitrack audio and captions directly on the operator’s computer. Audio tracks are available as MP3 files at session end; captions can be saved as Word documents.

Plan your signal path

Bring your audio setup and we’ll help map the channels.

For routing questions, equipment planning, or a technical walkthrough, contact the Interpreter24 team.

Talk to a technician →