Hacker News with Generative AI: Speech Synthesis

Llasa: Llama-Based Speech Synthesis (llasatts.github.io)
Recent advances in text-based large language models (LLMs), particularly in the GPT series and the o1 model, have demonstrated the effectiveness of scaling both training-time and inference-time compute.
DECtalk Archive (dectalk.nu)
DECtalk is a speech synthesizer, originally released as a hardware module in 1984 by Digital Equipment Corporation (DEC).
ByteDance Releases MegaTTS3 (github.com/bytedance)
Orpheus-3B – Emotive TTS by Canopy Labs (canopylabs.ai)
Show HN: Mist v2 – next gen conversational speech synthesis (rime.ai)
Introducing Mist v2, the world's fastest conversational text-to-speech model
ESpeak-ng: speech synthesizer with more than one hundred languages and accents (github.com/espeak-ng)