# Multi-voice Support
Erax Smile UnixSex F5
Vietnamese text-to-speech model based on F5-TTS architecture, supporting neutral-style voice cloning
Speech Synthesis Other
E
erax-ai
120
9
Orpheus 3b Chinese FT Q8 0.gguf
Apache-2.0
Orpheus is a high-performance text-to-speech model, fine-tuned specifically for natural emotional speech synthesis. This repository hosts the 8-bit quantized version of the 3-billion-parameter model, optimizing efficiency while maintaining high-quality output.
Speech Synthesis Supports Multiple Languages
O
lex-au
58
0
Orpheus 3b FT Q2 K.gguf
Apache-2.0
Orpheus is a high-performance text-to-speech model, specifically fine-tuned for natural emotional speech synthesis. This repository hosts the 8-bit quantized version of the 3-billion-parameter model, optimizing efficiency while maintaining high-quality output.
Speech Synthesis Supports Multiple Languages
O
lex-au
287
3
Speecht5 Tts Common Voice Uk
MIT
A Ukrainian text-to-speech model fine-tuned based on Microsoft's SpeechT5 architecture, trained using the Common Voice dataset
Speech Synthesis
Transformers Other

S
ewigeki
47
3
Featured Recommended AI Models