Halo NeuroAI open-sources Sopro V2 Turbo, a 120M on-device voice-cloning TTS model
Sopro V2: private, fast, on-device text-to-speech
Halo NeuroAI released Sopro V2, a family of text-to-speech models, and open-sourced its fastest member sopro-v2-turbo, a 120M-parameter voice-cloning model that streams on a laptop CPU or in the browser and covers English, German, French and European Portuguese. On an Apple M3 CPU it generates offline at 0.24 RTF and streams with about 300 ms to first audio at 0.21 RTF, while a single H100 reaches 0.07 RTF offline. The model was built through four training stages, including distillation from a 0.5B teacher and reflow that cut acoustic solver steps from 32 to 2, and the authors report 1.63 WER on Seed-TTS test-en and 1.79 on LibriSpeech test-clean under the F5-TTS protocol.
Source:Hacker News · AI · research.haloneuro.ai