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.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.