Audio8 Releases Audio8-TTS-Preview-0.1b: Zero-Shot Multilingual Voice Cloning

Audio8 · hf · 2026-08-23

Audio8 has released Audio8-TTS-Preview-0.1b on Hugging Face. This is a 0.1B parameter text-to-speech (TTS) model that supports multilingual synthesis. It features zero-shot voice cloning capabilities, allowing it to mimic voices without fine-tuning for specific speakers. The model is built on the Transformers architecture, uses the safetensors format, and integrates arktts technology.

Original post →

More from Multimodal

• Seeking Audio Upscaling LLMs: Is There a 'Super-Resolution' Model for Music? — LeatherRub7248 · 2026-08-24
• Describe your dream world to an AI dragon, which generates the planet for you — repligate · 2026-08-24
• Using kintsugi texture to fix cracks in edited 3D meshes — repligate · 2026-08-24
• Generating Hannibal Character Videos with FL2VA Model — Nimblecloud13 · 2026-08-24
• MiniMax H3 Revives Medieval Short Stories: Complete Workflow Shared — zanatas · 2026-08-24
• NAPE Audio Pretraining Achieves SOTA Without Decoders — kastnerkyle · 2026-08-24

Multimodal channel →