# How to Build an Interpreter Glossary with AI (Step by Step)

> To build an interpreter glossary with AI, give ChatGPT or Claude the assignment's real source material, ask for a bilingual term list with definitions and register notes, then verify every term against an authoritative source such as a specialist dictionary, an official terminology database, or the client. Load the verified list into your live tools so names and jargon appear correctly. Unicaption's custom dictionary does this for live captions, with side-by-side translation in 60+ languages and nothing stored after the session.

Published 2026-09-30 · The Unicaption Team · Human-readable version: https://unicaption.com/blog/ai-glossary-building-for-interpreters.html

## What AI is good at, and where it fails you

General-purpose assistants like ChatGPT and Claude are strong at the mechanical parts of glossary work: extracting candidate terms from a long document, grouping them by sub-topic, proposing equivalents in a target language, and drafting a one-line definition so you remember what each term means in context.

They are weak at exactly the part that matters most in the booth or on the call: knowing which equivalent is the one this field, in this country, actually uses. A model will happily produce a fluent, plausible, wrong term, especially for newer concepts, regional variants, and institution-specific vocabulary.

- ⚠ **Invented equivalents.** The term looks right and doesn't exist in the target-language literature.
- ⚠ **Wrong variant.** Correct in one country or dialect, unusual in the one you're working in.
- ⚠ **False friends and register.** A technically correct word that's too formal, too clinical, or too casual for the setting.
- ⚠ **Out-of-date usage.** Official terminology changes; a model's training data may not reflect the current form.

## The five-step workflow

**1. Start from real source material**
Paste in the agenda, the slide deck, the contract, the case summary, or the program notes, whatever the client has actually shared. A glossary built from the real document is far more useful than one built from a generic prompt like "medical terms for cardiology".

**2. Ask for a structured draft**
Request a table: source term, target-language equivalent, a one-line definition, register or usage notes, and a confidence flag. Ask the model to mark anything it isn't sure of, then treat the unmarked terms with suspicion too.

**3. Verify against an authoritative source**
Check each term in a specialist dictionary, an official terminology database, published standards, or a parallel text in the target language from the same field. When the stakes are high, ask the client or a subject expert. This is the step that can't be skipped.

**4. Sort by what you'll actually need**
Split the list into terms you must have instantly (names, numbers, acronyms, the five concepts the meeting is about) and terms you only need to recognize. Memorize the first group, keep the second as a reference.

**5. Load it where you'll use it**
A glossary on a laptop in another window helps less than one built into your tools. Load verified names and terms into the dictionary of whatever captioning or CAI tool you use during the assignment.

## Prompts that produce usable drafts

The difference between a useless list and a useful one is usually the prompt. Be specific about the language pair, the country, the setting, and the format you want back. A pattern that works:

- **Context first.** "I'm interpreting a two-hour supplier negotiation between a Turkish manufacturer and a German buyer. Attached is the draft term sheet."
- **Ask for extraction, not invention.** "List the specialized terms that appear in this document, in order of importance."
- **Name the output.** "Return a table: Turkish term, German equivalent, short definition, register note, and how sure you are."
- **Ask for what to double-check.** "Flag any term where the German equivalent varies by region or has more than one common form."

> Check what you're pasting before you paste it. Treat confidential client material according to your NDA and the client's rules. If you can't share a document with a general-purpose tool, build the term list from a public version, or from your own notes.

## Where each tool fits in your prep

|  | ChatGPT / Claude | Spreadsheet or term base | Live captioning tool |
| --- | --- | --- | --- |
| Best at | Drafting and organizing quickly | Storing your verified terms long-term | Showing the right term live, during the session |
| Biggest risk | Confident wrong terms | Gets stale if not maintained | Only as good as the terms you load |
| When you use it | Night before the assignment | Before and after every job | During the assignment |
| Verification | Always required | You are the source of truth | Check unusual terms in the transcript |

## Closing the loop: from glossary to live session

The glossary you've verified is only useful if the names and terms show up correctly when the speaker says them. Unicaption is a real-time captioning and translation copilot for interpreters, and its custom dictionary is built for this step.

- ✓ **Custom dictionary** for names, products, and specialized terms, so they appear spelled correctly in the live captions
- ✓ **Built-in medical, legal, and government terminology** as a baseline, with your own list on top
- ✓ **Live captions with side-by-side translation** in 60+ languages, so you can confirm a number or a name at a glance
- ✓ **Works beside any call or room**, using the microphone or system and tab audio, in the browser, on macOS and Windows, or with the Chrome extension
- ✓ **Nothing kept:** end-to-end encrypted, audio never stored, transcripts deleted when the session ends, and never used to train models

It's a copilot, not a replacement: the live text is a reference for you, and the interpreting is still yours. See [how to improve live caption accuracy](/blog/improve-live-caption-accuracy.html) and [custom dictionaries and terminology accuracy](/blog/custom-dictionary-terminology-accuracy.html) for how the dictionary works in practice.

## After the assignment: keep what you learned

The best glossaries grow. After each job, move the terms that actually came up into your permanent term base, delete the ones you guessed wrong, and note the ones the client corrected. That feedback loop is worth more than any model: over a year it becomes a resource tuned to your languages, your clients, and your fields.

If you're still putting your pre-assignment routine together, the [interpreter prep checklist](/blog/interpreter-prep-checklist.html) covers the rest of the night-before work, and [the best AI tools for interpreters](/blog/best-ai-tools-for-interpreters.html) compares what's available for each stage.

## Frequently asked

**Can ChatGPT or Claude build a glossary for an interpreting assignment?**
They can draft one quickly: extract terms from your assignment documents, propose target-language equivalents, and add short definitions. But they can also produce fluent terms that don't exist or aren't used in your country, so every term must be verified against a specialist dictionary, an official terminology source, or the client before you rely on it. Unicaption's custom dictionary then loads the verified list into your live captions.

**How do I check whether an AI-suggested term is correct?**
Look it up in a specialist dictionary or official terminology database for your field, find it in a parallel text written by native professionals in that field, or ask the client or a subject expert. If you can't confirm the term, don't use it as if it were fact. Treat AI output as a candidate list, not a reference.

**Is it safe to paste confidential assignment documents into an AI chatbot?**
Only if your NDA, the client, and the tool's data policy allow it. Many assignments forbid sharing material with third-party tools. When in doubt, build the glossary from public information or your own notes. Unicaption is built for live sessions: it is end-to-end encrypted, never stores audio, deletes transcripts at the end of the session, and never uses content to train models.

**What is a custom dictionary in a live captioning tool?**
It's a list of names, products, acronyms, and specialized terms you give the tool so it spells them correctly when speakers say them. In Unicaption you add your terms before the session, and they appear correctly in the live captions alongside built-in medical, legal, and government terminology.

---

*[Unicaption](https://unicaption.com) is a real-time AI captioning and translation copilot for human interpreters — live captions and translation in 60+ languages, end-to-end encrypted, nothing stored. 30 free minutes every week, no credit card required.*