Where Taiwa fits.

It's very good at some calls and mediocre at others, and the difference isn't subtle. Point it at the right queue and it pays for itself. Point it at the wrong one and you'll be disappointed in a way we could have warned you about.

Where it works

Transactional calls. The ones where the words carry the meaning.

Where's my order · Change my address · Rebook this · Reset my password · Is this in stock · Track my delivery · Confirm my appointment · Return this item

These calls are an exchange of information. The customer needs a fact, or needs you to change one. What matters is that the postcode is right and the date is correct — not the melody of how it was said. Translation carries facts extremely well.

This is most of a service desk's volume, and it's the volume that's currently being transferred, held, or called back.

Where it's harder

Calls where how it's said matters as much as what is said.

A complaint that's escalating · A customer who's upset · A negotiation · Anything where you're reading the room

Here the meaning isn't only in the words. It's in the pause before the answer, the edge in the voice, the sentence that trails off. Taiwa translates the words accurately. In 8 languages DeepL's newest voice model now carries some of the tone across too; in the rest, the translated voice stays calm whatever it's carrying.

So in most languages a furious customer can still arrive sounding composed. That's a real problem.

Medical, legal, safeguarding and financial-advice calls aren't on this page at all. Those need a certified human interpreter.

Where Taiwa stops →

How it's said

The words always come across. The way they're said, only in some languages.

How something is said carries meaning the words don't — intonation, stress, the rising tone that turns a statement into a question. "I didn't say that" means four different things depending on which word you lean on, and a translation that carries only the words flattens all four into the same sentence.

Taiwa runs on DeepL Voice, whose newest voice model, Aure, carries tone, emotion, emphasis and pace into the translated speech, automatically, in 8 languages: English, German, Spanish, French, Italian, Japanese, Portuguese and Korean. In every other language the translated voice is neutral, and emotion, sarcasm, hesitation and urgency don't come through it.

In 14 languages the translation can also be spoken in a voice close to the speaker's own; the others use a preset voice. Either way, the original voice keeps playing underneath (below).

So you still hear them

The original voice doesn't go away.

The obvious way to build this is to mute the customer and play a translation over the top. We don't. Their real voice keeps playing underneath the translation, quietly — 20% by default, and you can move it.

So your agent hears the translated words and the person saying them. The frustration, the hesitation, the relief, the speed they're talking at. Whatever the translated voice doesn't carry is still arriving on the original channel, because we never took it away.

It works both directions. Your customer hears your agent's actual voice under the translation too — the warmth, the apology, the care, in the voice that actually said it.

Some of the emotion now comes through the translation. None of it is deleted.

Inbound and outbound levels, in settings. 20% is the default.

The other constraint

The other thing that shapes fit is the delay. Fast back-and-forth pays the lag on every exchange; calls where each side speaks in longer turns barely notice it.

Why there's a delay, and what we do about it →

If you're trialling this, start here

Point it at your highest-volume transactional queue in a language you don't cover — order status, delivery, account changes. That's where the arithmetic is best and the limitations matter least.

Don't start with complaints. It'll work, but you'll be judging the hardest case first, and you'll conclude something about the tool that's really about the queue.

What is this costing you today? →

Not sure which queue?

Tell us what your calls are actually about when you request access. If they're the wrong kind, we'll say so.