Unverified50% confidenceFactExact time
GPT-SoVITS is an open-source few-shot voice cloning and synthesis project that combines GPT-style autoregressive modeling with the SoVITS acoustic model; it can clone a timbre from only a few seconds to a few tens of seconds of target audio, and its official pretrained models mainly cover languages such as Chinese, English, Japanese, and Korean.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedGPT-Live uses an end-to-end voice model that directly processes audio waveform input and outputs audio waveforms without going through text conversion in between.76% similarUnverifiedv0.23.0 switches the voice module's default STT model to gpt-transcribe.75% similarUnverifiedGPT-Live 采用端到端语音-语音翻译（S2ST）技术，在潜在空间完成跨语言语义映射，绕过文本中间表示并保留说话者音色、语调等副语言学特征74% similarVerifiedMultimodal models such as GPT-4o already support native processing of real-time audio.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1057789API
curl https://kongchang.com/api/v1/knowledge/claims/1057789MCP
get_claim(id=1057789)