Open-Source Frontier Voice AI
Repository Index
64,764 visible repositories in the index
1–16 of 16 · Most stars
YuE2: frontier music generation with symbolic planning, zero-shot covers, and agentic music editing.
- foundation-models
- music-generation
- huggingface
- llama
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
- transformer
- conformer
- speech-translation
- streaming-asr
pix2code: Generating Code from a Graphical User Interface Screenshot
- deep-learning
- datasets
- deep-neural-networks
- front-end-development
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.
- c-plus-plus
- machine-learning
- online-learning
- contextual-bandits
Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
- llm
- on-device-ai
- sdk
- vlm
Eagle: Frontier Vision-Language Models with Data-Centric Strategies
- demo
- eagle
- gpt4
- huggingface
Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.
An advanced singing voice synthesis system with high fidelity, expressiveness, controllability and flexibility based on DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism
- acoustic-model
- diffusion
- midi
- singing-voice
Ideogram 4: Open image model at the forefront of design
[NeurIPS 2026] Safety failures in coding agents and frontier LLMs. Reproducible workspaces for studying when AI agents generate unsafe data during task completion.
backend, web frontend, etc.
Localize your websites with AI assistance.
Code for Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention
Push-to-talk voice dictation for Linux. 100% local, multilingual (25+ languages), with speaker diarization. Qt frontend, Rust backend on NVIDIA Parakeet via ONNX Runtime. KDE Plasmoid integrated.
- asr
- linux
- nvidia
- parakeet
Implementation of "Adversarial Frontier Stitching for Remote Neural Network Watermarking" in TensorFlow.
- tensorflow
- tensorflow2
- watermarking
- neural-network