Qwen3-TTS voice cloning is now in mainline llama.cpp — the old demo finally became real support
英文标题：Qwen3-TTS voice cloning is now in mainline llama.cpp — the old demo finally became real support
People may remember the Qwen3-TTS llama.cpp demo from a few months ago. That PR said it probably wouldn’t be merged because llama.cpp was missing some of the graph and API pieces it needed. A new implementation was merged into master yesterday. What works now: - Qwen3-TTS-12Hz-1.7B-Base in GGU
打开原文相关 2 · 机会 2
中文
People may remember the Qwen3-TTS llama.cpp demo from a few months ago. That PR said it probably wouldn’t be merged because llama.cpp was missing some of the graph and API pieces it needed. A new implementation was merged into master yesterday. What works now: - Qwen3-TTS-12Hz-1.7B-Base in GGU
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
People may remember the Qwen3-TTS llama.cpp demo from a few months ago. That PR said it probably wouldn’t be merged because llama.cpp was missing some of the graph and API pieces it needed. A new implementation was merged into master yesterday. What works now: - Qwen3-TTS-12Hz-1.7B-Base in GGU