Edge0 releases Audio8-TTS-Realistic voice cloning model
MarkTechPost: Edge0 Releases Audio8-TTS-Realistic, a 0.6B Voice Cloning TTS Model
Edge0 has released Audio8-TTS-Realistic, an open-weight text-to-speech model for zero-shot voice cloning. Audio8-TTS-Realistic is a 0.6B-parameter model that clones a voice from 1 reference clip and transcript. It supports 23 languages, 12 more than its predecessor. The weights and code ship under Apache 2.0. For developers, the catch is competitive multilingual accuracy at a size that is cheap to fine-tune and serve. TL;DR Size: 601M main-model parameters (codec excluded); up to 2,048 p
Get smart on it
Audio8-TTS-Realistic is an open-weight text-to-speech model that can clone voices from a single reference audio clip and its transcript, supporting 23 languages with 601 million parameters. The model matters because it achieves competitive accuracy on standard benchmarks while remaining small enough to be inexpensive to fine-tune and deploy compared to larger alternatives. The model uses a two-branch architecture where a slow branch predicts text tokens and the first audio codebook, while a fast branch predicts remaining codebooks in parallel, and training incorporates a learned "realism critic" that scores outputs against human recordings to improve naturalness beyond standard metrics like word error rate and speaker similarity.
Relevant courses
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on MavenRelated news
Gemini 4 Carbon: Our next frontier model
Google's latest offering suggests the company is prioritizing efficiency and environmental impact alongside raw capability gains.
Also reported by Ars Technica, MarkTechPost, The Verge and The Decoder
Introducing GPT-6.1 Terra
Bringing fast and capable computer use to everyone
Also reported by SiliconANGLE, MarkTechPost and The Decoder
Welcome Le Chonk: Mistral Large 4 on Hugging Face
Mistral's latest offering aims to compete with frontier models while remaining accessible to researchers and developers on open platforms.
Also reported by SiliconANGLE and TechCrunch
Genie 4: A new generation of world simulation
Genie 4: our new world model unlocking unprecedented realism in real-time simulation.
Also reported by TechCrunch, Ars Technica, SiliconANGLE and MarkTechPost
Le Chonk: Built for Coders, Trusted by Defenders.
The weights of Mistral Large 4 (Le Chonk) are now open. A 1T parameter multimodal model, and best open-weight model for coding, trained in Europe.
NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt
Customizable transcription tools could help organizations reduce manual annotation costs while handling multiple languages simultaneously.
Also reported by TechCrunch, SiliconANGLE, The Decoder and MarkTechPost