Fish Audio 发布 Drama 3，支持对语音中单个词进行重生成
Fish Audio 新出的 Drama 3 能只改配音里错的那个词，其他不动，不用整段重录，还支持 83 种语言，做播客和配音的可以试试。
Fish Audio 发布语音合成模型 Drama 3，引入音频局部重绘功能，用户可以只替换录音中出错的词或短语，其余部分保持不变。传统 TTS 出错后往往需要整段重录，Drama 3 的工作流是先生成配音、选中要改的词、再单独生成替换片段。该模型支持 83 种以上语言的语音生成与局部编辑。
This is the first audio model I've seen that lets you edit individual words.
Text-to-Speech models have gotten really good lately, but they still make mistakes, and I hate having to redo an entire voiceover because one word is wrong.
@FishAudio just released Drama 3, and it supports audio inpainting.
Basically, you can regenerate a word or phrase inside your audio while keeping everything else unchanged.
The workflow is simple:
1. Generate your voiceover 2. Choose the word or phrase you want to replace 3. Generate the replacement and keep the rest of the take
It works surprisingly well!
By the way, you can do this in 83+ languages!
Thanks to the Fish Audio team for partnering with me on this post.
- AI Breakfast14:00原文
