Qwen3-TTS voice cloning is now in mainline llama.cpp — the old demo finally became real support

Article automatically generated from technical news.

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 GGUF - WAV or MP3 files as the speaker reference - English, Chinese, German, Italian, Spanish, French, Portuguese, Russian, Japanese and Korean - Audio generation through the llama