car

Thanks, I’ve changed the submission title from the author’s original.

Thanks, I concur and have changed the author’s original title to better represent the article.

Please make this more generic, using the OpenAI API standard with model discovery. That way it works against a bare Llama.cpp instance out of the box, the local inference server that many others wrap around (like Ollama and LM Studio).

This uses the new onboard TTS model from Apple, which is amazing, even with background noise.

The choice of model could be up to the user, depending on the available RAM on their M class Mac. Newer and bigger usually being smarter.

Llama.app/.cpp and Unsloth Studio on Mac already provide guidance to pick the optimal model for the available memory, all model wheights hosted by huggingface. Both apps can use the local huggingface model cache locally.

If you make it configurable, the user could also run a separate machine with an NVidia card and Linux to serve tokens on the LAN. Or use OpenRouter or any other cloud hosted model offering (DeepSeek, Z.ai, etc.).