Ask HN: What are you go to LLM models for the following
1. Coding 2. TTS (Text to Speech) and STT (Speech To Text) 3. Image creation and understanding
For me I've been using:
1. qwen3-coder-next 2. Fish Audio S2 Pro (TTS) and Whisper for STT 3. Gemma for image analysis and Flux for creation.
I run these on my 16-inch MacBook Pro (Apple M5 Max chip with 18-core CPU, 40-core GPU, and 16-core Neural Engine
) with 128GB unified memory Your use of Fish Audio S2 Pro for TTS on your MacBook Pro aligns well with the goals of speech-swift (which I maintain), offering robust integration with CoreML for ASR and TTS. It could serve as an alternative with its native Swift async support on Apple Silicon. Explore more here: https://github.com/soniqo/speech-swift