MarkTechPost63

Edge0 Releases Audio8-TTS-Realistic, a 0.6B Voice Cloning TTS Model

Name: AI HOT 精选数据集（復刻站）
License: https://aihot.yuenlau.org/llms.txt

2026/10/30 13:02· 2小时前

AI 摘要

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. The post Edge0 Releases Audio8-TTS-Realistic, a 0.6B Voice Cloning TTS Model appeared first on MarkTechPost .

查看原文（MarkTechPost）