We develop our own AI models for audio and video generation, editing, and understanding. They power Descript's video editing workflows.
A two-stage system — a continuous neural codec plus a flow-matching transformer — that regenerates a masked span of speech conditioned on surrounding audio and target text, zero-shot, with inaudible boundaries.
A training-free, inference-time scheduler that replaces left-to-right rollout with anchor-bounded tree imputation — converting horizon-compounding drift into bounded drift, and running 5.3× faster than autoregressive baselines.
Alexandre de Brébisson, Kundan Kumar, and Jose Sotelo founded Lyrebird in 2017, while studying under Yoshua Bengio at Mila. In 2019, after pioneering research in AI-generated speech and media synthesis, Lyrebird was acquired by Descript. While the team has evolved, its focus remains locked on developing technologies that power creative tools and advance the state of generative media.
