The Decision Record: How Creative Directors Direct an MLDM

01.The decisions you direct today

Translation comes back first. Where a line can land more than one way, the review step returns three renderings, each for a different intent and emotion, with the reasoning behind each. Your creative directors pick one or write their own, then render.

The same review covers the localization calls: the slang kept as said, the name kept, a reference swapped for one the audience knows, what that culture avoids, and the profanity lowered for a younger cut.

A pun, Korean to English

"사과하려고 사과 사 왔어." rests on 사과 meaning both apology and apple. Three renderings come back:

• "Apples. I'm sorry, right down to the core." The pun kept.
• "I came to say sorry. I brought apples." The meaning only.
• "An apple a day keeps the silent treatment away." A new joke.

The creative director picked the first and edited it.

A jab, Chinese to English

"你可真行啊。" reads as praise or as a jab, depending on the scene:

• "Wow. You're incredible." Sincere.
• "Well, aren't you something." Sarcastic, the pick.
• "Look at you, hotshot." Teasing.

A podcast, an episode or a movie carries many such segments: the jokes, the conversations, the stories.

02.The audio decisions

The MLDM decides what to translate at all. It finds the main voice, carries it into the new language in the speaker's own voice, and keeps the rest as it was. Showing your team every close call in the audio is in the works.

What stays in the original language: a stadium chant, kept in Korean; a yell across a kitchen; a catchphrase the fans know. The background speaker no one can make out stays as it was, or comes back as a choice to translate after all.

03.The visual decisions

In the works. Who is actually saying it: the face a line is heard from, the narrator, the voice from off screen. When the model picks the wrong speaker, you pick the face from the candidates, and the lips move on the right person.

The text in the frame: the phone screen reading 내일 봐, a street sign, a store front. Each item is written in the terms you already chose, as "See you tomorrow", or kept as shot.

The expressions and gestures follow the new line's emphasis or the culture. An eyebrow raise the new audience reads differently can be held as shot.

04.Recorded with the dub

The record is what makes an MLDM a new paradigm, the first of its kind: a model that shows its decisions. The decision record, in the works, holds every decision with its options, the reasoning, what was chosen and by whom: the model, you, or memory.

It is open at review and locked at render. Change a decision on a delivered dub and render again; only the languages it touches render again. A dub rendered with review=autostill writes the record, with the model's choices.

05.A choice made once follows the next episode

In the works: decision memory. Remember an override for a creator, one show, channel or person, and the next dub applies it first when the same line, term, name, chant, sign or face comes back. The catchphrase kept in the original follows episode 2 without a second review.

Two standing decisions work today. Do Not Translate keeps a phrase as said, and Context gives the one-sentence briefing; you set both before the dub. The record holds the decisions the model made during it.

06.On the review screen and in the API

In the works: the review screen grows a decisions rail. A timeline of the episode carries a marker per decision, filtered by translation, audio or visual; each card shows the moment, the options with the reasoning and the model's pick lit. One tap picks another option, types your own, keeps the original, or remembers the choice for this creator.

The API returns the same record, so a choice made on the screen shows in the API and the other way round. The planned surface, all in the works:

• GET /v1/dubs/{dub_id}/decisions reads the record.
• PATCH /v1/dubs/{dub_id}/decisions/{decision_id} overrides one decision.
• The decisions.* settings on a new dub set how many renderings come back, the profanity level, and which calls come back to you.
• The dub.decisions_ready webhook fires when the record is open.
• decisions.json carries the full record with every delivered dub.

The reference is at Decisions; today's review step is at Transcript & review.

QUESTIONS

REFERENCES

1. [1]What Is a Multimodal Localization Decision Model (MLDM)?
2. [2]API: Decisions
3. [3]API: Transcript & review