llama.cpp adding more TTS models; drama-3 35B and ZONOS3 GGUFs already live
ngxson · x · 2026-11-16
ngxson, a core llama.cpp contributor, announced that more TTS (text-to-speech) models are coming to llama.cpp, with "even more soon."
The accompanying ggml-org TTS collection on Hugging Face has been updated with freshly uploaded drama-3-GGUF (35B), ZONOS3-Mini-GGUF (0.8B), and Soprano-1.1-80M, alongside earlier entries like the chatterbox series (800 downloads), Qwen3-TTS-1.7B (59k downloads), and sesame-csm-1b — a fast-expanding ecosystem for running speech synthesis fully locally.
Related event: llama.cpp Accelerates Local TTS Support with New GGUF Models(3 posts)→
More from Infra
- Liquid AI d1-2B decision model runs on-device: ~68ms gesture reading, 14 decisions/s, zero tokens — AccBalanced · 2026-11-16
- Microsoft Outlook outage silenced chlorine alert emails at German theme park, injuring 15 pool guests — AccBalanced · 2026-11-16
- Ming-Chi Kuo: OpenAI and Anthropic orders extend Google TPU visibility to 2029, ~26M units — BenBajarin · 2026-11-16
- Cerebras core revenue up 70% YoY to $231M, backlog hits $26.1B — AccBalanced · 2026-11-16
- Nvidia CEO saga: firstadopter discusses Jensen Huang's resignation and successor race on TBPN — firstadopter · 2026-11-16
- Bittensor week: Lium hits $35M annualized GPU rental run rate — bittingthembits · 2026-11-16