| ▲ | teravor 5 hours ago | |||||||
kokoro is decent but pocket-tts is much better especially when you rip a good voice. https://github.com/kyutai-labs/pocket-tts the onnx version of pocket-tts does perform better. https://huggingface.co/KevinAHM/pocket-tts-onnx | ||||||||
| ▲ | psanford an hour ago | parent | next [-] | |||||||
I agree, pocket-tts is quite good. It is also very easy to make new voices from small sample files with pocket-tts. | ||||||||
| ▲ | mscdex 5 hours ago | parent | prev [-] | |||||||
I've found that for CPU inference the PyTorch-based (non-quantized) version of Pocket TTS actually performs (both speed and quality-wise) better than the ONNX version, even after fiddling with all of the knobs that ONNX provides. | ||||||||
| ||||||||