Skip to content
local-ai

Beyond LLMs

Image generation, speech recognition, text-to-speech, and other local models.

  1. Intermediate

    Local image generation

    You can generate images entirely on your own GPU. The models worth knowing, the tools that run them, and the licensing catch that trips people up.

  2. Intermediate

    Speech to text and text to speech

    Local models transcribe speech and generate it, well enough for real use and light enough to run on modest hardware. The models, the tools, and the trade-offs.

  3. Intermediate

    Embedding models for search and RAG

    Not every local model generates text. Embedding models turn text into vectors, which powers semantic search and RAG. How they work and how to choose one.

  4. Intermediate

    Local video generation

    Open text-to-video has recently become runnable on consumer hardware. What the models do, which ones fit your GPU, and the trade-offs in memory, length, and licensing.

  5. Intermediate

    Local music and audio generation

    Generating music and audio from a text prompt, locally. What the models can do, which run on modest hardware, and why the licence is the first thing to check.