The defining fact of this queue is that the modality changes as often as the topic — phone, video, onsite. Here's how to run a live transcription and translation layer beside whichever one is on today's schedule, privately.
A phone queue in the morning, a video assignment with a hospital system in the afternoon, an onsite appointment the next day — interpreting through LSA (Language Services Associates) means the modality itself keeps changing, not just the subject. A live captioning layer doesn't erase that switching cost — it gives you one steady tool that follows you across every modality. This page is a practical guide to running one beside phone and video assignments, written for the interpreter, not the agency.
LSA works across healthcare systems, insurers, government agencies, and corporate clients in industries like manufacturing and hospitality, and it offers phone, video, and onsite interpreting rather than just one. That range means an interpreter's week can include a phone queue for an insurer's claims line, a video assignment for a hospital's intake desk, and an onsite appointment for a government office — three different presentation styles for three different clients, sometimes in the same week.
The tiring part of covering phone, video, and onsite work isn't any one modality — it's rebuilding your working setup and your presentation style every time the format changes. Phone interpreting is audio-only and fast; video interpreting adds framing, eye contact, and on-screen composure; onsite adds travel, room logistics, and reading a physical space. None of those skills fully transfers to the others, so switching between them carries a real cost even when the subject matter is familiar.
| Modality | What it actually demands |
|---|---|
| Phone (OPI) | Full reliance on audio — no visual cues, fastest to connect, easiest to lose a detail with nothing to look back at |
| Video (VRI) | On-camera presence, screen-based turn-taking, and the added self-consciousness of being visibly framed |
| Onsite | Travel time, room dynamics, and no transcript safety net unless you bring your own |
Unicaption is a real-time captioning and translation copilot that runs on your computer, beside whatever assignment is on today's schedule. It listens to your microphone or your system audio — it never dials in, never joins a video call, and never appears to the client or the patient:
If you're comparing copilots built specifically for interpreters, our honest comparison with Interpreter maps where each one fits.
Confirm today's modality and audio source once — mic for a headset call, system audio for anything that plays through the computer speakers. On a video assignment, position the window somewhere it won't distract you from the screen.
Interpret the way you always do; the transcript is a backup, not a script. It's most useful for the things a switch in modality tends to knock loose — a number, a name, a term you only half-caught while adjusting to a new format. Our guide to captioning phone calls in real time covers the audio setup this depends on.
Reset for the next modality, not just the next topic. The gap between a phone queue and a video assignment is often the only time you get to recalibrate.
Add anything new to your dictionary while it's fresh — a term is worth capturing once, regardless of which modality you heard it on.
LSA's client list spans hospital systems, insurers, government offices, and corporate accounts, which means the sensitivity of what crosses your line changes as often as the modality does — protected health information one assignment, financial account details the next. The standard you hold yourself to shouldn't change with the format.
Unicaption's design assumes that standard regardless of modality: sessions are end-to-end encrypted, audio is never stored, transcripts are deleted the moment the session ends, and session content is never used to train models. For more on the compliance side specifically, see our guide to HIPAA-compliant live captioning.
That depends on LSA's own policies, which you should check directly — we won't pretend to speak for them. What Unicaption does is run locally beside your call or session, reading only your microphone or system audio; it never joins or records anything, never stores audio, and deletes transcripts when the session ends. It is end-to-end encrypted with nothing retained after the session. Whether an aid is appropriate for a given assignment is a professional judgment that stays with you.
No. Unicaption runs in a separate window on your own device and reads only your microphone or system audio — it doesn't capture, join, or inject anything into the video call itself, so the client or patient sees nothing on their side. It's still worth confirming with LSA's own guidance, since video assignments sometimes carry their own expectations about what's visible on your screen.
For phone and video work, yes — it reads mic or system audio beside either one identically, with the same accuracy and translation either way. Onsite interpreting doesn't route through a computer's call audio the same way, so its usefulness there depends on your own setup; most interpreters use it mainly for their phone and video assignments.
Every account gets 30 free minutes each week, no credit card required, and the free minutes renew weekly regardless of how many modalities you work in. Paid plans run from Instant at $9/month to Ultra at $149/month, with annual discounts. Spend a few weeks of free minutes across a real mix of assignments before paying anyone.
30 free minutes every week, no credit card. Nothing joins the call, nothing appears on screen but yours.
Start Free Trial →