AI Briefing#audio-cpp
The latest AI and developer news about #audio-cpp, with the original source and a short summary.
The latest AI and developer news about #audio-cpp, with the original source and a short summary.
Higgs Audio TTS now runs in under 6GB VRAM, while HTDemucs sees a 2.21x speedup on CUDA.
audio.cpp version 0.6 has been released, supporting five new model families including MiniMax-H3 and a WebUI.
audio.cpp 0.5 adds expressive TTS, multilingual voice transfer, and AMD GPU support.
audio.cpp 0.4 adds Higgs Audio v3 TTS and Fish Audio S2 Pro among others, now supporting 35 model families with Q8 GGUF improving speed and VRAM.
audio.cpp, a C++/GGML-based framework, has undergone a major update by adding music and SFX generation as well as source separation features.