audio-generation

Amphion is an open-source toolkit for audio, music, and speech generation, providing model visualizations, vocoders, and evaluation metrics to support reproducible research.

This article introduces how to use the new Gemini 3.8 text-to-speech model to create custom voices, including selecting voice types, adjusting characteristics, and applying it in multi-speaker scenarios.

OpenBMB releases VoxCPM2, a 2B-parameter tokenizer-free TTS model trained on 2M+ hours of multilingual speech data, supporting 30 languages, voice design, controllable cloning, and 48kHz output.

Google introduces Gemini Omni, a new multimodal AI model capable of processing and generating content across text, images, audio, and video from any input type.