skinny.

Latest / Kana & Mari's SoundRepos (English)

chinokikiss/GSV-TTS-Lite | low latency GPT SoVITS text to speech | GitHub

GSV-TTS-Lite is a high-performance Python inference backend and SDK for GPT-SoVITS V2, V2Pro, and V2ProPlus text-to-speech models. It provides low-latency streaming and batched synthesis, timbre-style separation, character-level timestamps, voice conversion, speaker verification, WebUI access, and asynchronous FastAPI services. Related: chinokikiss/GSV-TTS-Lite / low latency GPT SoVITS text to speech / GitHub

The skinny

The skinny isn't ready yet — notes appear once the transcript is processed.