Tencent Hunyuan open-sources AuK, a unified speech generation and editing model
- Source
- x.com
- Date
🚀 AuK is officially here. Nano banana🍌 for audio An open-source foundation model for unified speech generation and editing. Natural-language instructions + reference audio. One interface. Zero-shot TTS. Instruction-controlled generation. Content editing. Whisper-conversion. De-accent. Timbre/style/emotion edit. Speed/Pitch control. Enhancement, denoising, multi-speaker and music separation. Also releasing AuK-Flash: 4-step inference. ~4.5× faster under matched conditions. Code, weights, and demo are live. Try it and share your feedback. 🤗 Paper & upvote: https://t.co/zEveUsuJRF ⭐ GitHub & star:
Context
Tencent Hunyuan open-sourced AuK, a single foundation model that takes natural-language instructions plus a reference audio clip and handles zero-shot text-to-speech, instruction-controlled generation, and content editing such as changing timbre, style, emotion, speed, or pitch, alongside transcription, de-accenting, denoising, and multi-speaker or music separation. Tencent Hy also released AuK-Flash, a variant using 4-step the company says runs about 4.5 times faster under matched conditions.
- distillation — Training a small, cheap model to imitate a big one's outputs, keeping much of the capability at a fraction of the cost.
- inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
Checking sign-in…
Loading comments…