High-fidelity text-to-speech models for Tamazight. Advancing speech synthesis for the Amazigh language through open-source AI and open science.
-
Higgs Audio v3 TTS (100 languages)
🍋13Zero-shot TTS & voice cloning with Higgs Audio v3 (4B)
-
multimodalart/higgs-audio-v3-tts-4b-transformers
Text-to-Speech • 5B • Updated • 40.1k • 18 -
k2-fsa/OmniVoice
Text-to-Speech • 0.6B • Updated • 877k • 1.24k -
bosonai/higgs-tts-3-4b
Text-to-Speech • 5B • Updated • 374k • 697