Free, open-source AI video generator for Mac. Run LTX-2.5 and MiniMax H3 (Hailuo) locally on Apple Silicon: text-to-video and image-to-video with sound, lip-sync, character LoRA training, songs from lyrics (YuE2) and image editing (Qwen-Image-Edit). One-click install via Pinokio. Offline: no cloud, no API key, no NVIDIA GPU.
Python ai-filmmakingai-videoai-video-generatorapple-siliconhailuoimage-to-videolip-synclocal-ailora-trainingltx-2ltx-2-5ltx-videomacosminimax-h3mlxmusic-generationoffline-aipinokiotext-to-videovideo-generation
# Speech engine venv (speech-mlx/.venv, Python 3.12): the known-good set.
# Resolved from mlx-audio 0.5.8 (2026-10-05) on 2026-10-22; every package exact.
# The ONLY install into that venv is scripts/speech/speech_setup.sh packages (-c this file).
# Not the LTX venv's set on purpose: mlx-audio needs mlx>=0.32, LTX holds 0.31.1.
annotated-doc==0.0.5
anyio==4.15.1
cffi==2.1.1
click==8.5.0
filelock==4.2.4
fsspec==2026.9.0
h11==0.16.0
hf-xet==1.7.0
httpcore2==2.16.0
httpx2==2.16.0
huggingface-hub==2.2.0
idna==3.20
markdown-it-py==4.2.0
mdurl==0.1.2
miniaudio==1.71
mlx==0.32.4
mlx-audio==0.5.8
mlx-metal==0.32.4
numpy==2.5.4
packaging==26.3
pycparser==3.12
pygments==2.21.0
pyyaml==6.0.3
regex==2026.9.29
rich==15.0.0
safetensors==0.8.0
scipy==1.18.1
shellingham==1.5.4
sounddevice==0.5.6
tokenizers==0.23.3
tqdm==4.70.1
transformers==5.20.2
truststore==0.10.5
typer==0.27.3
typing-extensions==4.16.0