[GH-ISSUE #1667] Can it replace Elevenlabs? #1110

New issue

Closed

opened 2026-10-20 10:06:01 +00:00 by bsakaguchi · 3 comments

bsakaguchi commented

2026-10-20 10:06:01 +00:00

Owner

Originally created by @rutvik106 on GitHub (Dec 30, 2023).
Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/1667

I just want to know that is it possible to use this tool on my AWS Server to create voices for my voice cloning product? Currently I am using Elevenlabs to do it. And it is very costly.

Originally created by @rutvik106 on GitHub (Dec 30, 2023). Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/1667 I just want to know that is it possible to use this tool on my AWS Server to create voices for my voice cloning product? Currently I am using Elevenlabs to do it. And it is very costly.

bsakaguchi

2026-10-20 10:06:01 +00:00

closed this issue
added the
stale
label

bsakaguchi commented

2026-10-20 10:06:01 +00:00

Author

Owner

@H46K3RL0L commented on GitHub (Dec 31, 2023):

Don't quote me on this, but it should be possible with some changes to the code. I think these would be pretty big changes though because this is voice CONVERSION, not voice GENERATION.

@H46K3RL0L commented on GitHub (Dec 31, 2023): Don't quote me on this, but it should be possible with some changes to the code. I think these would be pretty big changes though because this is voice CONVERSION, not voice GENERATION.

bsakaguchi commented

2026-10-20 10:06:02 +00:00

Author

Owner

@78Alpha commented on GitHub (Jan 1, 2024):

It needs to be combined with a TTS tool. This just applies the voice properties to audio. You have some options for TTS with ups and downs.

Tortoise (Old, slow, but allows for synthesizing completely new voices and cloning existing voices with accent)
XTTS (Clone a single voice or multiple voices as different speakers, including accent)
Piper (Clones a voice, no emotion and slow to train)
StyleTTS (Can learn the style of a voice and clone it, allowing for control of emotional inflection, but needs 24 GB VRAM+ for training)
SUNO (It can make voices, lots of features, no real voice cloning. A voice can be cloned but not trained, so it will have poor quality)
Built-ins (AWS, Azure?, Edge, so on)

@78Alpha commented on GitHub (Jan 1, 2024): It needs to be combined with a TTS tool. This just applies the voice properties to audio. You have some options for TTS with ups and downs. - Tortoise (Old, slow, but allows for synthesizing completely new voices and cloning existing voices with accent) - XTTS (Clone a single voice or multiple voices as different speakers, including accent) - Piper (Clones a voice, no emotion and slow to train) - StyleTTS (Can learn the style of a voice and clone it, allowing for control of emotional inflection, but needs 24 GB VRAM+ for training) - SUNO (It can make voices, lots of features, no real voice cloning. A voice can be cloned but not trained, so it will have poor quality) - Built-ins (AWS, Azure?, Edge, so on)

bsakaguchi commented

2026-10-20 10:06:02 +00:00

Author

Owner

@github-actions[bot] commented on GitHub (Apr 28, 2024):

This issue was closed because it has been inactive for 15 days since being marked as stale.

@github-actions[bot] commented on GitHub (Apr 28, 2024): This issue was closed because it has been inactive for 15 days since being marked as stale.