基本信息
- 来源: blogs_podcasts
- 原始来源: https://openai.com/index/descript
来源摘要/节选
公开展示已截断至最多 800 个字符;请访问原始来源查看完整上下文。
Using OpenAI reasoning models, Descript unlocked automatic localization of large content libraries without losing timing or meaning.
Percentage point improvement in duration adherence with OpenAI
Increase in dubbed exports post-rollout
Descript (opens in a new window) is an AI-native video editor built around a simple idea: if you can edit text, you should be able to edit video. Since Descript’s early days, AI has powered every aspect of the product: transcription, editing, audio cleanup, and increasingly complex creative workflows. They’ve built on OpenAI for years, using Whisper for transcription and GPT series models inside their co-editor Underlord.
Translation quickly emerged as a high-impact use case.…
来源说明
当前只保存了公开页面节选,不代表原文全文。请以原始来源为准。
本页只呈现已做哈希绑定的来源证据,不包含基于旧正文或缺失原文的扩展推断。