0.5B
Fish Speech V1.5-SOTA Open Source TTS
Towards OCR-2.0 via a Unified End-to-end Model
CosyVoice2-0.5B-Scalable Streaming Speech Synthesis with Large Language Models
i2v-14B-720p-2.1
flux-1.dev
PuLID-FLUX-v0.9.0
8B TTS
This model is not yet booted but ready for API calls. Your first API call will boot the model and may take longer, but after that subsequent responses will be fast.
This model runs on L40S.