AI engineering glossary · Generative media multimodal
What is audio language model?
Audio language model: A model that treats discrete audio tokens as a sequence and predicts them autoregressively, like a text language model, allowing generation of speech, music or sound continuations from a prompt.
Audio language model: an example
Given 3 seconds of a piano tune as tokens, the model generates the next 10 seconds in the same style.
Related terms
- Neural audio codec
- Zero-shot TTS
- Autoregressive image generation
More Generative media multimodal terms
- Beta-VAE
- BLIP
- Classifier-free guidance
- CLIP score
- Codebook
- Conditional GAN
- Consistency model
- Content provenance
Where you learn it
Audio language model is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.