---
format: "aidr-story-markdown/v1"
id: "88860537ecad4e2bd9b8c95e9d3e4b4c6f4be5fa36e7662ea3f6ca9a5fa51c20"
canonical_url: "https://aidr.today/88860537?lang=en"
title: "Edge0 Releases Audio8-TTS-Realistic, a 0.6B Voice Cloning TTS Model"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-30T05:02:52.000Z"
category: "Models"
topics: ["open-source"]
source_urls: ["https://www.marktechpost.com/2026/10/29/edge0-audio8-tts-realistic-0-6b-voice-cloning/"]
summary: "Edge0 released Audio8-TTS-Realistic, a 0.6B open-weight zero-shot voice cloning TTS model under Apache 2.0 that supports 23 languages and adds a final GRPO stage driven by a learned realism critic."
---

# Edge0 Releases Audio8\-TTS\-Realistic, a 0\.6B Voice Cloning TTS Model

> [Open the canonical story](<https://aidr.today/88860537?lang=en>)

**Published:** 2026-10-30T05:02:52.000Z
**Category:** Models
**Topics:** open\-source

## Summary

Edge0 released Audio8\-TTS\-Realistic, a 0\.6B open\-weight zero\-shot voice cloning TTS model under Apache 2\.0 that supports 23 languages and adds a final GRPO stage driven by a learned realism critic\.

## Sources

- [Story source](<https://www.marktechpost.com/2026/10/29/edge0-audio8-tts-realistic-0-6b-voice-cloning/>)