0xShug0/audio.cpp🔥 active
An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.
High Performance Serving Runtime For Interactive Super Intelligence System
$ git clone https://github.com/sgl-project/sglang-omni.gitAn all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.
▲ +3 ★ this week
The hub for audio AI research: papers, open models, benchmarks & datasets across audio LLMs, speech recognition, TTS, music & audio generation.
Scene-aware storyboard for DeepSeek Harness: 9-16 numbered cells with timestamps + transcript + an audio envelope, packed into ONE image (384 tokens). Two tools: video_storyboard and video_zoom.
▲ +14 ★ this week
audio.cpp with a full-task WebUI - pure C++ audio-model inference engine powered by ggml. TTS, ASR/STT, VAD, voice conversion, speaker diarization, music generation. No Python dependency.
▲ +8 ★ this week
Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images
AI sovereignty for the world's most trusted runtime.
Data from GitHub · snapshot Nov 16, 2026