Models / SWivid / E2 TTS

E2 TTS

JSON →
audio

A text-to-speech model designed for efficient and expressive speech generation with minimal latency.

audiostreaming
homepage ↗
Specs
Context & limits
—
context window
—
max output
Lifecycle
Dates
released2024-05-01
Resources
homepagehttps://huggingface.co/SWivid/E2-TTS ↗