Tencent has released AuK-Flash, a distilled version of its 1.5B parameter speech generation and editing model, AuK. This new variant is designed for fast, four-step inference. AuK-Flash, along with the base AuK model, supports a wide range of speech tasks including zero-shot and instruction-based text-to-speech, content and acoustic editing, speech enhancement, and source separation, all controllable via a natural language interface. The models are available on Hugging Face and ModelScope. AI
IMPACT Accelerates speech generation and editing capabilities with a focus on speed and versatility.
RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →