Tag
Edge0 released Audio8-TTS-Realistic-0.6B, a compact 0.6B DualAR text-to-speech model with improved speech realism, zero-shot voice cloning, and support for 23 languages (12 more than the Preview version), bundled with a 44.1 kHz neural audio codec and an SGLang serving adapter.
This paper investigates the Mimi codec's semantic tokens, showing they map to phonetic units like quadphones and triphones, and discusses implications for speech tokenization in AI models.