ainewsblitz.com

Breaking

OpenMOSS Releases MOSS-TTS-Nano, a 0.1B-Parameter Multilingual Speech Model That Runs on CPUs Without a GPU

OpenMOSS Releases MOSS-TTS-Nano, a 0.1B-Parameter Multilingual Speech Model That Runs on CPUs Without a GPU
  • Media Generation
  • Open Source
  • Foundation Models

OpenMOSS has released MOSS-TTS-Nano, a compact 0.1-billion-parameter open-source text-to-speech model that generates real-time multilingual speech and clones voices directly on a CPU, eliminating the need for a GPU. The model, built by the OpenMOSS team associated with the Fudan NLP Lab, targets lightweight, low-latency deployment on edge devices, local machines and browsers where heavier speech systems have traditionally been impractical.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,908 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year