Open source · 31 October 2026
Available nowEdge0 launches Audio8-TTS-Realistic 0.6B open-weight voice cloning model
Edge0 released Audio8-TTS-Realistic, a 0.6 billion‑parameter open‑weight TTS model that performs zero‑shot voice cloning. The model supports 23 languages, adds a final GRPO stage driven by a learned realism critic, and is licensed under Apache 2.0.
Why it matters
Audio8‑TTS‑Realistic’s zero‑shot voice cloning and 23‑language support may raise user expectations for multilingual TTS; evaluate it for upcoming products.
For product managers
For your product
What does this mean for your product?
Try it on your product More from this issueAll AI news from 31 Oct →
Get this every morning, written for your product.
Deltaday reads the whole AI news cycle and tells you what changed, whether it's real yet, and what to do about it.