ai-multilingual-dubbinglisted

# AI Multilingual Dubbing Create organized narration audio for every target market from scripts the user provides or approves. Reuse the message, destination, languages, voice direction, segment boundaries, and timing targets already visible in the conversation. Move by the shortest route to a representative pilot, then produce the rest of the approved audio scope. ## Start from the spoken scripts Build a `segment × locale` production matrix. Each cell records the locale and BCP-47 tag, approved text, protected terms, pronunciation notes, voice, delivery direction, format, timing target, and status. Use natural segments such as a scene, lesson, chapter, ad, or publishable message—never a mid-sentence split. If the source exists only as video or audio, use an actually available host capability to obtain a transcript or ask the user for one. Keep that transcript as draft text until the user approves what will be spoken. The speech operation accepts text, not source media. When localization is requested, help draft the target-language wording in the conversation, preserve product names, claims, numbers, units, URLs, and calls to action, and obtain content approval. Do not claim professional or native-language review unless the user supplies that fact. Use [matrix design](references/matrix-design.md) and [locale readiness and quality](references/locale-readiness-and-quality.md) for the complete preparation and review gates. ## Choose a voice and a useful pilot Reuse an acc