Among the interpreters who rely on it, the verdict is consistent: at last, something built for the way they actually work. The premise is simple. Interpreting works best as human and machine together, not machine in place of the human.

Interpreting is one of the hardest things a person can do in real time. The interpreter has to listen, understand, reframe and speak almost at once, often through an unfamiliar accent or a run of numbers that arrives faster than anyone could write it down. Researchers describe a “tightrope hypothesis”: for most of an assignment, interpreters work at the very edge of their mental capacity, and accuracy slips as soon as that load rises. The strain is physical, too. Time pressure raises stress and heart rate, and quality declines in turns longer than half an hour, which is why interpreters are rotated roughly every 30 minutes.

That pressure has only grown as the work moved online. Interpreting is an $11.7 billion industry by Nimdzi’s estimate, and a growing share of it now happens remotely: over video, through uneven audio, in hybrid meetings that barely existed five years ago. The captioning systems interpreters could reach for were never built for them. Intercall was built to close that gap.

Built for the interpreter

Intercall is a real-time, human-in-the-loop captioning and translation platform made for one audience: professional interpreters. Human-in-the-loop means exactly that. The human stays in charge, the software assists. While the interpreter works, Intercall puts everything being said on screen, as text, in both languages, the moment it is spoken.

Its founder, Bahodir Rajabov, started from something most products miss. An interpreter does not need a tidy transcript after the meeting; they need the right word in the moment, fast enough that it does not break their concentration. The name they did not catch. The figure that went by too quickly. The technical term from a field they do not work in every day.

Rajabov started programming at 14 in Bukhara, Uzbekistan, and later joined IBM’s generative-AI team. He built Intercall to solve a problem the rest of the market had overlooked, and he was the primary architect of its core: the native audio capture, the low-latency transcription pipeline, the terminology system and the cross-platform desktop workflow. The general captioning systems available to interpreters ran three to five seconds behind the speaker. That is fine for subtitles. It is a real problem for a medical interpreter relaying symptoms as they are spoken, or in a courtroom where half a second can change what a statement means.

As he puts it: “Nobody had built anything for interpreters. They are masters of their craft, working with borrowed tools. Captions made for viewers, translation apps made for travelers. They just needed something made for them.”

How it works

The turning point was leaving the browser. Intercall runs as native software on the interpreter’s own machine, installed like Word or Zoom itself rather than opened as a website. Written in C++, it works directly with the operating system and takes the audio straight from whatever call is open, whether Zoom, Microsoft Teams or Google Meet. There is no browser extension, no meeting bot and no screen-sharing.

It does three things. It transcribes the conversation as it happens, fast enough that the text stays level with the speaker instead of trailing behind. “It has to feel instant,” Rajabov says. “The moment the text falls behind the speaker, it is useless, and interpreters simply close it.” It catches the parts that are easiest to lose and most expensive to get wrong, the proper nouns and specialist terms, and it lets interpreters load as many as 600 of their own before a session: the cardiology vocabulary before a cardiology appointment, the case names before a hearing. And in a multilingual call it moves between languages and dialects on its own, across dozens of them. The doctor’s English and the patient’s Russian, captured side by side, in one conversation, the way interpreted calls actually happen.

For most interpreters, that one window replaces a patchwork of tools built for other people: meeting captions, a notepad, a translation tab kept open in the browser. The difference shows up in the work itself. Fewer requests for repetition. Long, dense passages relayed without breaking the conversation’s flow. Far less of the frantic note-taking that drains interpreters by the end of a shift, so the energy that went into catching and holding details goes back into the interpreting.

Intercall is built to assist, not to take over. It does not interpret for the user. It surfaces what would otherwise slip past and hands it back, leaving the interpreter in charge of the part only a person can do: the meaning and the judgment. That choice put Intercall early into a human-in-the-loop category that analysts now track, AI that supports professional interpreters during live work rather than replacing them. The bigger names have since moved the same way. Boostlingo added an AI productivity tool in 2024, KUDO brought assistance into its interpreter console in 2025, and analysts at Slator and Nimdzi now cover the category.

Confidentiality

Interpreters raise the obvious objection almost immediately: if it is AI, is it storing my audio and training on my clients’ private conversations? The company’s answer is in how the platform is built, not in a privacy policy. According to Intercall, audio, transcripts and translations live only in memory and are gone when the session ends; nothing is written to a server, and nothing is used to train the models. Whatever an interpreter generates stays theirs. It is encrypted, and built for the confidentiality that HIPAA-regulated medical work and the courts demand, the settings where a leaked transcript is a breach, not an inconvenience.

Adoption and impact

Intercall has been running for more than a year and a half. More than 3,000 professional interpreters across 18 countries have used it, and thousands of hours of live interpretation now run through the platform every month. What stands out is the reach. The largest group of users is in the Dominican Republic, with paying interpreters also across the United States, Poland, Peru, Honduras, Mexico, Canada and beyond, many of them working through interpreting providers including Propio Language Services, iCall International and others. They use it on live assignments in hospitals, courtrooms and conference halls. Its growth has come mostly through the profession itself: interpreters recommending it to colleagues, and saying so in public.

The impact they describe comes down to two words: efficiency and accuracy.

Efficiency, because the tool absorbs the part of the job that exhausts interpreters, holding names, numbers and details in memory while still listening and speaking. Interpreters report working longer hours with far less fatigue. Some describe ending shifts with energy they used to burn on frantic note-taking. A few say it pulled them back from burnout that had nearly pushed them out of the profession. In a field where the working limit is mental fatigue rather than skill, that is the difference between a sustainable career and an early exit.

Accuracy is the other half. Everything said on a call is transcribed and translated in real time, in both languages, in front of the interpreter, so requests for repetition drop sharply and the details most expensive to get wrong, drug names, dosages, case numbers, addresses, stop slipping through. In a hospital, that means the patient who speaks no English receives discharge instructions exactly as the doctor gave them. In a courtroom, it means testimony enters the record complete.

One interpreter at Propio Language Services in Colombia, remote for more than five years, described working 48-hour weeks with paper notes and a Boogie Board: “By the end of the day, I often felt mentally exhausted from constantly relying on memory and note-taking.” Even with generic caption tools running, “I still had to manually write down phone numbers, addresses, names, and other critical details… the cognitive load was always there.” Then he found Intercall: “It has significantly reduced my mental workload and allowed me to focus on what matters most: interpreting accurately and serving my clients effectively. No more juggling a notepad, translators, and multiple reference tools. I genuinely cannot imagine working without it.”

Independent practitioners say much the same. In a detailed review, the interpreter Nourhane Atmani wrote that it “does reduce unnecessary cognitive load, helps us catch what we might otherwise miss (names, numbers, etc.), and supports us when working in demanding or unfamiliar contexts,” while making clear that it “does NOT replace interpreters (and never aims to).” Another put it more plainly: “It is like working with a co-pilot. I am still flying the plane. Now I have better instruments.”

What comes next

Intercall is built and run by a lean, dedicated team, and the company is now focused on scaling: reaching more interpreters, and bringing the platform to interpreting agencies and enterprise teams. The engineering work follows the same line, with most of the effort going into one stubborn problem: holding accuracy in the noisy, low-quality audio interpreters so often have to work with.

That discipline has earned the field’s trust. “We started as an assistant. We proved our accuracy and earned that trust first,” Rajabov says. “You cannot skip that stage. It is where the others went wrong.”

The interpreter stays at the center of the work, listening, weighing and turning one language into another in real time. Intercall is not there to take that over. It is there, in Rajabov’s phrase, to give them a second pair of ears.