How do audio and speech LLMs work, and how do discrete audio tokens differ from text tokens?

Speech LLMs either transcribe to text or model audio directly as discrete tokens. The signal is the semantic-vs-acoustic token split and why end-to-end audio models beat ASR-plus-LLM pipelines on latency and prosody.

Updated Aug 2026 · Grounded in real Applied AI Engineer interview loops and written to a senior-engineer editorial bar.