Seed Voice Conversion V2 (Voice & Style Conversion)

Zero-shot voice/style conversion with in-context learning. For local deployment please check GitHub repository for details and updates.
Note that any reference audio will be forcefully clipped to 25s if beyond this length.
If total duration of source and reference audio exceeds 30s, source audio will be processed in chunks.
Please click the 'convert style/emotion/accent' checkbox to convert the style, emotion, or accent of the source audio, or else only timbre conversion will be performed.
Click the 'anonymization only' checkbox will ignore reference audio but convert source to an 'average voice' determined by model itself.
无需训练的 zero-shot 语音/口音转换模型，若需本地部署查看GitHub页面
请注意，参考音频若超过 25 秒，则会被自动裁剪至此长度。
若源音频和参考音频的总时长超过 30 秒，源音频将被分段处理。
请勾选 'convert style/emotion/accent' 以转换源音频的风格、情感或口音，否则仅执行音色转换。
勾选 'anonymization only' 会无视参考音频而将源音频转换为某种由模型自身决定的 '平均音色'。
Credits to Vevo, MegaTTS3

Seed Voice Conversion V1 (Voice & Singing Voice Conversion)

Zero-shot voice conversion with in-context learning. For local deployment please check GitHub repository for details and updates.
Note that any reference audio will be forcefully clipped to 25s if beyond this length.
If total duration of source and reference audio exceeds 30s, source audio will be processed in chunks.
无需训练的 zero-shot 语音/歌声转换模型，若需本地部署查看GitHub页面
请注意，参考音频若超过 25 秒，则会被自动裁剪至此长度。
若源音频和参考音频的总时长超过 30 秒，源音频将被分段处理。