Audio processing

The Infinite Crate is a DAW plugin built on JUCE, React, and the Lyria RealTime live music model

NPM Library to transcribe Audio & Videos completely in browser with WebGPU and WebCodecs. 100% private and offline with WASM fallbacks

Real-time transcription and AI assistant for Meta Ray-Ban smart glasses. Live speech-to-text, speaker diarization, Gemini Live vision+voice, and WebRTC streaming.

A SOTA Industrial-Grade Voice Activity Detection & Audio Event Detection, supporting 100+ languages, outperforming Silero-VAD, TEN-VAD, FunASR-VAD and WebRTC-VAD

A beautiful Windows program for analyzing audio quality — detects fake lossless, clipping, MQA, and AI-generated audio; includes a spectrogram viewer and more. Built-in player with EQ and spatial audio.

Petal is a native macOS menu bar app for fast, local-first audio transcription.

cliamp - Terminal music player inspired by winamp

Slap your MacBook, it yells back. Uses Apple Silicon accelerometer via IOKit HID.

Rust implementation of Qwen3-ASR automatic speech recognition

A tiny audio streaming server (compatible with icecast2) written in Go with multiple mountpoint, multi-source, and relaying support and a lot more.

A desktop music player built with Electron that streams audio from YouTube Music. Clean UI, no accounts, no ads.

WhisperCrabs is a simple terminal-based floating recording button, click, and transcribe to input

Ming-omni-tts: Simple and Efficient Unified Generation of Speech, Music, and Sound with Precise Control

🌋LavaSR: Fast Speech restoration and enhancement

A real-time and multilingual speech translation model

Pure C inference of Mistral Voxtral Realtime 4B speech to text model

Your voice is the fastest interface to AI

🎵 The Ultimate Open Source Suno Alternative - Professional UI for ACE-Step 1.5 AI Music Generation. Free, local, unlimited. Stop paying for Suno!

ComfyUI custom nodes for Qwen3-ASR (Automatic Speech Recognition) - audio-to-text transcription supporting 52 languages and dialects.

Open source macOS video transcriber that builds a self-organizing knowledge base 🐝

Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.