Descript Research
We develop our own AI models for audio and video generation, editing, and understanding. They power Descript's video editing workflows.
What we work on
Audio editing by latent inpainting
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.
Anchored tree sampling beats autoregressive drift
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.
Our ethics
Descript believes a person's likeness is part of their identity. We pledge to do our part to help individuals retain control of their voice.
Publications
Goodbye Drift: Anchored Tree Sampling for Long-Horizon Video-to-Video Generation
May 19, 2026
Read paper
About Descript Research
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.
© Descript 2026