工具POST
Qwen3.8-LiveTranslate separates speakers by voice
In multi-speaker turn-taking conversations, the model labels each utterance with spk1, spk2 and similar tags and keeps each speaker's voice in the translated speech.
小互
@xiaohuArchived 2026.09.20Originally posted 2026.09.19
小互 @xiaohuOriginally posted 2026.09.19
在多人轮流发言或交替对话时，模型会用 spk1、spk2、spk3 这样的标签区分每句话是谁说的，并让对应的译文语音保留各自的音色。 https://t.co/myqdINGVHx
x.com/xiaohu/status/2101339337887772936Archived 2026.09.20 11:18