[GH-ISSUE #1544] model features #1019

New issue

Open

opened 2026-10-20 10:05:10 +00:00 by bsakaguchi · 2 comments

bsakaguchi commented

2026-10-20 10:05:10 +00:00

Owner

Originally created by @artem671 on GitHub (Nov 14, 2023).
Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/1544

is it possible to use the model to translate text into voice, or does it work only with voice? I just had an idea to make a voice assistant with her help, but so far nothing is working

Originally created by @artem671 on GitHub (Nov 14, 2023). Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/1544 is it possible to use the model to translate text into voice, or does it work only with voice? I just had an idea to make a voice assistant with her help, but so far nothing is working

bsakaguchi added the

good first issue

label

2026-10-20 10:05:10 +00:00

bsakaguchi commented

2026-10-20 10:05:10 +00:00

Author

Owner

@Tps-F commented on GitHub (Nov 16, 2023):

It is possible by using the RVC structure.
It would need to be used in conjunction with the Text2Speech structure

@Tps-F commented on GitHub (Nov 16, 2023): It is possible by using the RVC structure. It would need to be used in conjunction with the Text2Speech structure

bsakaguchi commented

2026-10-20 10:05:11 +00:00

Author

Owner

@blakejrobinson commented on GitHub (Nov 16, 2023):

is it possible to use the model to translate text into voice, or does it work only with voice? I just had an idea to make a voice assistant with her help, but so far nothing is working

It feels like this is probably outside the scope of RVC, but it's possible (if a little in-depth). If you're decent with python you can whip something up with a module such as Silero TTS, Whisper TTS, etc. to generate regular TTS and then just run their results through the inferer.

@blakejrobinson commented on GitHub (Nov 16, 2023): > is it possible to use the model to translate text into voice, or does it work only with voice? I just had an idea to make a voice assistant with her help, but so far nothing is working It feels like this is probably outside the scope of RVC, but it's possible (if a little in-depth). If you're decent with python you can whip something up with a module such as Silero TTS, Whisper TTS, etc. to generate regular TTS and then just run their results through the inferer.