A modular Swift SDK for audio processing with MLX on Apple Silicon
💬 Fast, cross-platform CLI and GUI for batch transcription, translation, speaker annotation and subtitle generation using OpenAI’s Whisper on CPU, Nvidia GPU and Apple MLX.
A high-performance, fully local real-time voice translation agent built for Apple Silicon. Features seamless English-Hindi translation, zero-shot voice cloning, and a stateful agentic workflow orchestrated by LangGraph and MLX-Audio.
Text-to-speech for Claude Code hear responses, notifications, and command completions spoken aloud.
PageMatch transcribes your audiobook once using NVIDIA's Parakeet model running locally on your Apple Silicon GPU via MLX. After that, finding any moment in a 20-hour book takes under a second — just paste a sentence from the text.
这是一个基于 mlx-audio 的本地 REST 服务，用来实现兼容 OpenAI 的 TTS / STT 音频接口桥接层。
Transcribe and translate audio and video files using the IBM Granite 4.0 1B Speech model on Apple Silicon with MLX.
Voxtral 4B TTS 2603 on mlx
A state-of-the-art Web UI for Qwen3-TTS providing zero-shot voice synthesis, optimized natively for Apple Silicon (MLX) and Nvidia (CUDA) with PyTorch fallback integrations.
Generate multilingual speech with the Hexgrad Kokoro model on Apple Silicon with MLX.
Turn any web article or PDF into a private, narrated read-along on your Mac — local, offline, karaoke-style. Kokoro TTS via MLX-Audio.
Local meeting audio/video transcription skill with speaker diarization, subtitles, summaries, reports, and optional translation.
Add a description, image, and links to the mlx-audio topic page so that developers can more easily learn about it.
To associate your repository with the mlx-audio topic, visit your repo's landing page and select "manage topics."