watsonmusic

it's not oss

bonus usage

11labs is facing a real competitor

genius

this model is superb

Microsoft is cool

yes the best

one of the best models built by Microsoft

VibeVoice is a novel framework designed for generating expressive, long-form, multi-speaker conversational audio, such as podcasts, from text. It addresses significant challenges in traditional Text-to-Speech (TTS) systems, particularly in scalability, speaker consistency, and natural turn-taking. A core innovation of VibeVoice is its use of continuous speech tokenizers (Acoustic and Semantic) operating at an ultra-low frame rate of 7.5 Hz. These tokenizers efficiently preserve audio fidelity while significantly boosting computational efficiency for processing long sequences. VibeVoice employs a next-token diffusion framework, leveraging a Large Language Model (LLM) to understand textual context and dialogue flow, and a diffusion head to generate high-fidelity acoustic details. The model can synthesize speech up to 90 minutes long with up to 4 distinct speakers, surpassing the typical 1-2 speaker limits of many prior models.

cannot wait seeing how it goes beyond the current llm training pipeline

it could be adaptive. only high-value tokens were allocated with more compute

A new scaling paradigm finally comes out!

14b model performs comparably with 32b size. the improvement is huge

negative values can enhance the expressibility

not all hallucinations are creativity Imaginate that for a RAG application, the model is supposed to follow the given documents

the model is supposed to learn this

The modification is simple and beautiful. And the improvements are quite significant.

that would be huge!