StyleTTS 2

Published

Nov 20, 2023

StyleTTS 2 is an AI model developed by Columbia University (United States), first published in November 2023. It works in the speech domain, on tasks such as text-to-speech (tts) and speech synthesis.

Epoch AI has no training-compute estimate for this model. Training ran on 4 NVIDIA A40 PCIe.

Access: Open weights (unrestricted). Its weights are openly available.

Full record

Organization: Columbia University
Country of organization: United States
Domain: Speech
Task: Text-to-speech (TTS), Speech synthesis
Training hardware: NVIDIA A40 PCIe
Chips used: 4
Training power draw: 2.4 kW
Model accessibility: Open weights (unrestricted)
Open weights: Yes