2026-10-29 · America/Los_Angeles · 社区动态 · #15

Kokoro can now clone any voice with just ~600 MB of extra VRAM!

While looking for audio models, I came across OpenVoice. It's getting pretty old, but surprisingly still ranks high on TTS leaderboards. What caught my attention was its design: essentially TTS + voice conversion . The ToneColorConverter can run independently of the TTS model. That got me thinking: Can we pair it with other TTS models? I tried it with Kokoro, and the results were pretty good! So I added a small recipe any-tts to audio.cpp for Kokoro + OpenVoice ToneColorConverter. Recipes were introduced in v0.9.2 as predefined pipelines that combine multiple audio models. The overheads:…

热度 44.2 / 100；排名与评分保留该期记录。