Audio8 has released Audio8-TTS-Preview-0.1b, a compact text-to-speech model designed for practical zero-shot voice cloning. The model features a 170M parameter generative component and a 120M parameter neural audio codec, making it significantly smaller than many multilingual TTS systems. It supports primary languages of Chinese and English, with experimental support for German, Spanish, French, Italian, Japanese, and Korean. AI
IMPACT Enables more accessible and efficient zero-shot voice cloning due to its compact size.
RANK_REASON Release of a new, smaller-scale TTS model with specific technical details and usage instructions. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Hugging Face Trending Models →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
