Model
TTS-Next
An audio creative generation model from the Qwen team that employs a combined language model and diffusion model framework. It supports simultaneous generation of vocal, sound effects, and background audio within a single inference pass.
Timeline (last 90 days)
Sep 23
TTS-Next adopts a unified language model (LM) + diffusion model framework, capable of simultaneously producing vocals, sound effects, and background audio in a single generation pass.
Unverified50%