You are using an out of date browser. It may not display this or other websites correctly. You should upgrade or use an alternative browser.
english mandarin
About this tag
The tag 'english mandarin' on WindowsForum.com covers discussions about text-to-speech technology that supports both English and Mandarin languages. Recent content highlights Microsoft's VibeVoice, an open-source framework capable of generating hour-scale, multi-speaker audio with up to four distinct speakers, including English and Mandarin demos. This technology combines a compact LLM planner, novel continuous tokenizers, and a diffusion-based acoustic decoder to produce coherent speech for up to 90 minutes. Safety features like audible disclaimers and imperceptible watermarks are also included. The tag is relevant for researchers and enthusiasts interested in multilingual TTS systems and their applications.
Microsoft’s new VibeVoice marks a striking shift in what open-source text-to-speech can do: from short, single-voice clips to hour‑scale, multi‑speaker spoken audio that resembles a produced podcast — and it’s available now for researchers and tinkerers to try. The framework packages a compact...
ai in windows
continuous_tokenizers
diffusion acoustic head
englishmandarin
gpu
hour-scale
llm planner
long form audio
multi-speaker
open source
podcast editing
research release
safety features
speech synthesis
text-to-speech
tts
vibevoice
watermark