Navigation section
hour-scale
About this tag
The hour-scale tag on WindowsForum covers Microsoft's VibeVoice, an open-source text-to-speech framework that generates hour-scale, multi-speaker spoken audio. Unlike traditional TTS limited to short clips, VibeVoice synthesizes up to 90 minutes of coherent speech with up to four distinct speakers, resembling a produced podcast. It packages a compact LLM planner with continuous tokenizers and a diffusion-based acoustic decoder, supporting English and Mandarin. Safety features include an audible disclaimer and an imperceptible watermark. This tag is relevant for researchers and developers exploring advanced, open-source TTS capable of long-form, multi-speaker output.
-
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