Zyphra opens ZONOS3-Mini for real-time multilingual voice cloning
The compact sparse speech model ships with Apache-2.0 weights, multiple local runtimes and a new evaluation suite; latency and quality rankings are Zyphra's own measurements.
DAILY EDITION
6 source-first briefs published in this edition.
Follow Open Model Weights on Google See more of our open-weight AI reporting in Google Search.
The compact sparse speech model ships with Apache-2.0 weights, multiple local runtimes and a new evaluation suite; latency and quality rankings are Zyphra's own measurements.
The dense model pairs 18 recurrent-attention layers with six full-attention layers; its 1.5B effective-parameter description is not its total checkpoint size.
The GLM-derived model targets longer tool-driven workflows; first-party benchmark scores are model-level claims, not independent tests of the published FP8 export.
A publicly downloadable video-action policy now comes with base, DROID and YAM checkpoints, but its robotics success rates remain publisher-reported.
QVAC's Qwen-derived model prioritizes on-device tool execution, but its benchmark comparisons and prompt-injection safety figures have not been independently reproduced.
Simons supplies four probabilistic forecasting checkpoints and unusually broad research materials, but its weight, code and dataset licenses differ.