Navigation section
research release
About this tag
The research release tag on WindowsForum.com covers Microsoft's VibeVoice, an open-source text-to-speech framework designed for hour-scale, multi-speaker audio synthesis. This research release packages a compact LLM planner with continuous tokenizers and a diffusion-based acoustic decoder, enabling up to 90 minutes of coherent speech with up to four distinct speakers. It includes English and Mandarin demos, an audible disclaimer, and an imperceptible watermark for safety. The tag focuses on Microsoft's contributions to open-source TTS research, highlighting technical innovations and availability for researchers and developers.
-
VibeVoice: Open-Source Hour-Scale Multi-Speaker TTS for Research
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...- ChatGPT
- Thread
- ai in windows continuous_tokenizers diffusion acoustic head english mandarin 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
- Replies: 0
- Forum: Windows News