james-see/ltx-video-mac

Native macOS app for AI video generation using LTX-Video model, optimized for Apple Silicon

What it solves

LTX Video Generator for Mac provides a native macOS application to run the LTX-2 video generation model locally on Apple Silicon. It simplifies the complex process of setting up AI video generation, offering a user-friendly interface for creating videos from text or images with synchronized audio, voiceovers, and background music.

How it works

The app is built with SwiftUI and uses the MLX framework to optimize performance on M-series chips. It implements a two-stage pipeline: first generating a video at half resolution and then upsampling and refining it to full resolution. It supports multiple model variants, including unified audio-video models (LTX-2 and LTX-2.3) and a distilled Q4 version for lower memory usage.

Who it’s for

Mac users with Apple Silicon (M1-M4) and at least 32GB of RAM who want to generate AI videos locally without relying on cloud services, and those who want a integrated workflow for adding voiceovers (via MLX-Audio or ElevenLabs) and background music.

Highlights

  • Native Apple Silicon Performance: Optimized via MLX for M-series chips.
  • Integrated Audio: Generates synchronized audio automatically with video using unified models.
  • Multimodal Input: Supports both text-to-video and image-to-video generation.
  • Prompt Enhancement: Optional Gemma-powered prompt expansion to turn short descriptions into detailed, optimized prompts.
  • Complete Audio Suite: Local MLX-Audio or cloud-based ElevenLabs for voiceovers and 54 genre presets for background music.
  • Queue and History: Built-in management for multiple generations and a video archive for post-generation audio addition.

Related

  • Project
    jjang-ai/mlxstudio

    A native macOS app for Apple Silicon that provides a user-friendly interface to run LLMs, vision models, and image generation locally using the MLX framework.

  • Project
    raullenchai/Rapid-MLX

    A high-performance local AI engine for Apple Silicon that provides OpenAI and Anthropic-compatible APIs for running LLMs, audio, and video models natively on M-series Macs.

  • Project
    Blaizzy/mlx-audio-swift

    A modular Swift SDK for audio processing on Apple Silicon, providing on-device support for text-to-speech, speech-to-text, and speaker diarization using the MLX framework.

  • Project
    Blaizzy/mlx-audio

    MLX‑Audio is a Python library (with CLI, web UI, and Swift package) that runs a large collection of modern speech and music models on Apple Silicon via the MLX framework. It supports TTS, STT, speech‑to‑speech, voice cloning, VAD/diarisation, and music generation, offering quantised 3‑ to 8‑bit variants for low‑memory inference. Install with `pip install mlx-audio`, generate audio via `mlx_audio.tts.generate …` or the Python `load_model(...).generate` API, and optionally serve an OpenAI‑compatible REST API.

  • Project
    Blaizzy/nativ

    A native macOS app for running MLX models locally on Apple silicon, featuring a chat interface, image generation, and an OpenAI-compatible API server.