Seed-TTS

model paper
ByteDance
State-of-the-art speech generation model family known for high-fidelity voice cloning and expressive prosody.
Paper (arXiv)Project PageGitHub

Outputs 2

Seed-TTS

model

State-of-the-art speech generation model for high-fidelity voice cloning and expressive prosody.

GitHubProject Page

Seed-TTS: A Family of High-Quality Versatile Speech Generation Models

paper

Technical paper on the Seed-TTS family of speech generation models.

Paper (arXiv)

arXiv: 2406.02430

audiogeneration