audio

A video composition framework build on top of AVFoundation. It's simple to use and easy to extend.

Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

Open-source LLM-based ASR model family for Chinese, dialect, accent, and multilingual speech, with FunASR, vLLM, streaming, and llama.cpp runtimes.

🗜️Compress Image, Video, and Audio same like Whatsapp 🚀✨

Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine

Play simultaneously music/audio from assets/network/file directly from Flutter, compatible with android / ios / web / macos, displays notifications

The Hugging Face Course on Transformers for Audio

The dataset of Speech Recognition

HuggingSound: A toolkit for speech-related tasks based on Hugging Face's tools

Synthalingua - Real Time Translation

Transcribe and translate audio to text using Whisper and DeepL.

Joint speech-language model - respond directly to audio!

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.

LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM

[MIR-2023-Survey] A continuously updated paper list for multi-modal pre-trained big models

Code and Pretrained Models for ICLR 2023 Paper "Contrastive Audio-Visual Masked Autoencoder".

Radient turns many data types (not just text) into vectors for similarity search, RAG, regression analysis, and more.

[EMNLP2024 Demo], [ICASSP 2025], [ICASSP 2026] A user-friendly library for reproducible video moment retrieval and highlight detection. It also supports audio moment retrieval.

llama.cpp (GGUF LLMs) and llava.cpp (GGUF VLMs) for ROS 2

Golang framework to build an AI that can understand and speak back to you, and everything else you want