AIsaAIsaStudio 中文 Open AIsa Studio

Tontaube V1.1: open-weights TTS with voice cloning, 4-bit version runs near real time on a desktop CPU

Original title: Tontaube V1.1: open-weights TTS with voice cloning for long-form generation. 4-bit version runs about real time on a desktop CPU

Tontaube AI released Tontaube V1.1, a ~2.9B-parameter autoregressive TTS model with zero-shot voice cloning built for long-form audio such as audiobooks and voice agents. The default 4-bit GPTQ version (1.8 GB download) runs in about 4 GB of VRAM or roughly real time on a 12-core desktop CPU, and code is Apache 2.0 while weights use a community licence with free research and personal use.

Why it matters

The official release post details 4-bit VRAM requirements, CPU real-time inference, and blind listening results, helping readers gauge the barrier for local TTS deployment.

Read the original ↗

The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.