Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
GenerSpeechgenerspeech.github.io · Low evidenceGenerSpeech is a text-to-speech model designed for zero-shot style transfer of out-of-domain custom voices. It decomposes speech into style-agnostic and style-specific components using a multi-level style adaptor and a content adaptor with Mix Style Layer Normalization.
Parse Score