Launching today
apple-llm
Apple's free LLMs and speech for Node.js and Python
2 followers
Apple's free LLMs and speech for Node.js and Python
2 followers
Access Apple’s on-device LLM, macOS text-to-speech and speech recognition from Node.js and Python. Build local voice workflows with the SDK, CLI, or OpenAI/Ollama-compatible server. Requires macOS 26+ on Apple Silicon. The optional cloud tier sends prompts off-device.
Launch Team
LoomShow, don't just tell with Loom
Promoted
I built apple-llm to make the LLM, speech recognition and system voices already available on a Mac accessible from Node.js and Python. The latest release adds local text-to-speech and transcription, including subtitle and microphone workflows.
It requires macOS 26+ on Apple Silicon and the Xcode Command Line Tools. Speech works without Apple Intelligence; the on-device LLM needs it enabled. The optional Private Cloud Compute tier sends prompts off the Mac.
I would especially appreciate feedback from macOS 26 users and people trying real-world recordings.