KRAFTON Releases A.X-K2 Speech Model Supporting Any-to-Any Modality
KRAFTON · hf · 2026-08-02
KRAFTON's A.X-K2-Raon-Speech-21B-A3B model has landed on the Hugging Face trending list.
The model features 21B total parameters with 3B active parameters, utilizing a Mixture-of-Experts (MoE) architecture. It is designed as an any-to-any pipeline, with core tags covering speech, audio, automatic speech recognition (ASR), and text-to-speech (TTS).
More from Models
- Nous Research Co-founder Interview: Why Open-Source AI Must Win & How Hermes Avoids Slop — NousResearch · 2026-08-03
- Karpathy Highlights Simon Willison's 'Pelicans on Bicycles' LLM Eval Test — karpathy · 2026-08-03
- Same Price Tier, Different Worlds: DeepSeek V4 Outperforms GPT-5.6 in Canvas Tests — eyishazyer · 2026-08-03
- Mainstream LLM API Uptime Tested: Anthropic Lags, Kimi K3 Hits 99.4% — weswinder · 2026-08-02
- MiniMax Offers 1.7B Tokens for $20, Raising Third-Party Privacy Concerns — dark_bits · 2026-08-02
- MiniMax Launches Open-Weight Video Model H3, Topping Video Editing Benchmarks — NerdyRodent · 2026-08-02