News for hackers. Stuff that matters.

Show HN: Real-time local TTS (31M params, 5.6x CPU, voice cloning, ONNX)

https://github.com/ZDisket/vits-evo

Hi guys and gals, I made a TTS model based on my highly upgraded VITS base, conditioned on external speaker embeddings (Resemble AI's Resemblyzer).

The model, with ~31M parameters (ONNX), is tuned for latency and local inference, and comes already exported. I was trying to push the limits of what I could do with small, fast models. Runs 5.6x realtime on a server CPU

It supports voice cloning, voice blending (mix two or more speakers to make a new voice), the license is Apache 2.0 and it uses DeepPhonemizer (MIT) for the phonemization, so no license issues.

The repo contains the checkpoint, how to run it, and links to Colab and HuggingFace demos.

Now, because it's tiny, audio quality isn't the best, and as it was trained on LibriTTS-R + VCTK (both fully open datasets), speaker similarity isn't as good.

Regardless, I hope it's useful.

( 4 comments | 3 points | on HN )
Re:Show HN: Real-time local TTS (31M params, 5.6x CPU, voice... by popalchemist on Wednesday March 18, 2026 @07:59PM (#47432931)
given the architecture, is there a way to force the use of specific phonemes for hard-to-pronounce words? If so that's big
Re:Show HN: Real-time local TTS (31M params, 5.6x CPU, voice... by ZDisket on Thursday March 19, 2026 @06:14PM (#47447076)
Yes. Specifically, the pipeline is text -> phonemizer -> phonemized text -> TTS model -> audio You just have to modify the phonemizer's dictionary.
Re:Show HN: Real-time local TTS (31M params, 5.6x CPU, voice... by chenglin97 on Thursday March 19, 2026 @04:15AM (#47436348)
Does it support other languages than English? I’m Chinese speaker
Re:Show HN: Real-time local TTS (31M params, 5.6x CPU, voice... by ZDisket on Thursday March 19, 2026 @06:13PM (#47447051)
No multilingual capabilities yet, although that is planned for next iteration.