AIMarkTechPostabout 3 hours ago
Edge0 Releases 0.6B Voice Cloning Model
4 min read
Edge0 released Audio8-TTS-Realistic, a 0.6B-parameter text-to-speech model supporting 23 languages. It achieves a 4.86% average CV3 error, beating Qwen3-TTS-1.7B at 7.73%. The model runs on NVIDIA H20 GPUs or Apple M2 CPUs and uses Apache 2.0 weights.
Level
Hype check
Tap to vote and see what everyone thinks.
