AudioLM is a framework developed by Google Research for high-quality audio generation with long-term consistency. It maps input audio to discrete token sequences and treats audio generation as a language modeling task in this representational space. By training on a large corpus of raw audio waveforms, AudioLM learns to generate natural and coherent audio continuations, producing grammatically and semantically plausible speech segments even without text or annotations while preserving the speaker's identity and prosody. Furthermore, AudioLM is capable of generating coherent piano music continuations, even though no symbolic representation of music was employed during training.