Built for vocal conversion
Start with a recorded vocal performance, then use a compatible so-vits-svc setup to convert it into the trained voice.
Find so-vits-svc models for vocal covers, singing voice conversion, and other recorded voice projects. Each listing opens the exact model file or repository shared by its uploader.
Browse so-vits-svc voice models →Showing 24 of 32 · Page 1 of 2
Standalone artifact
by LeonTheEngSpanGuy
Standalone artifact
by redactedredact
Standalone artifact
by KingSGD915
Standalone artifact
by redactedredact
Standalone artifact
by LeonTheEngSpanGuy
Standalone artifact
by SZ0
Standalone artifact
by LeonTheEngSpanGuy
Standalone artifact
by Mikeprogamer
Standalone artifact
by AIHUBFRANCE
Standalone artifact
by redactedredact
Standalone artifact
by redactedredact
Standalone artifact
by rylee15
Standalone artifact
by yanayaco
Standalone artifact
by rylee15
Standalone artifact
by redactedredact
Standalone artifact
by redactedredact
Standalone artifact
by alicestarrs
Standalone artifact
by ShabiAI
Standalone artifact
by QuickWick
Standalone artifact
by 7kkurxes
Standalone artifact
by LeonTheEngSpanGuy
Standalone artifact
by YETI2003
Standalone artifact
by redactedredact
Standalone artifact
by MrYesser
Continue by voice, framework, language, franchise, category, or creator when that context is represented in these models.
Start with what you want to make: live voice changes, recorded speech, a song cover, or another vocal project. Then check the model's language, version, files, and app requirements.
Different versions of the same framework may need different tools or settings.
Do not assume a model's language from the character name alone.
Look for the required weights, configs, checkpoints, setup notes, demos, and app requirements.
No. Each listing links to the external page where the model was published.
Different creators, datasets, framework versions, and training runs remain separate models.
so-vits-svc converts an existing vocal performance into another trained voice while preserving the source melody and delivery. It is commonly used for singing and recorded conversion, not as a standalone text-to-speech generator.
AIVoices checks the exact downloadable model and looks for a matching so-vits-svc package or repository layout. Always read the original model card for setup instructions, license terms, and any restrictions from the uploader.
Check the voice, training version, language, included config files, and source instructions before downloading a model.
Start with a recorded vocal performance, then use a compatible so-vits-svc setup to convert it into the trained voice.
An unpacked model normally pairs a generator weight with its config. Packaged downloads may include those files in one ZIP.
Different so-vits-svc releases can use different model layouts and setup steps. Follow the instructions on the original source.