AIHacker Noonabout 10 hours ago
Edge0 Releases 0.6B Multilingual TTS Model
11 min read
Edge0 launched Audio8-TTS-Preview-0.6b, a 0.6-billion-parameter multilingual text-to-speech model supporting 11 languages and zero-shot voice cloning. The model uses a DualAR architecture and includes a bundled 44.1 kHz neural audio codec, eliminating the need for a separate codec checkpoint.
Level
Hype check
Tap to vote and see what everyone thinks.
Summary by ByteBrief
