Audio Language Model5 min read
Edge0 Releases Audio8-TTS-Realistic, a 0.6B Voice Cloning TTS Model
Edge0 released Audio8-TTS-Realistic, a 0.6B open-weight zero-shot voice cloning TTS model under Apache 2.0. It supports 23 languages and adds a final GRPO stage driven by a learned realism critic.
By Asif RazzaqMarkTechPost

Read the full story
Originally published by MarkTechPost on Oct 30, 2026.
Comments
Sign in to join the discussion.