Add Text to Voice Models

Feature RequestsNew ModelJan 15, 2025

Add a voice/speech mode to Venice, something like Kokoro-82M would be awesome https://huggingface.co/hexgrad/Kokoro-82M

Another great option is Zonos:

https://x.com/itspaulai/status/1889049392663130552?s=46&t=jD5k8zg6e_Ncz0bUDZ2u8w

Completed19

Team•

Mar 5, 2025

Pinned

Venice Voice was launched today and is available in the Text Settings menu. We’ll document it in tonight’s change log. Enjoy and thanks for your patience!

Jack
Team•
Mar 5, 2025
Try it out and send your feedback in the support channel and discord. Thanks everyone!
https://discord.gg/askvenice
[email protected]

How to enable Voice Mode:
https://venice.ai/faqs?identifier=voice+mode

Indigo Backpack

•

Feb 9, 2025

Add to character chat as well and let the user choose the characters voice!

Lime Spray
•
Feb 16, 2025
That would be excellent. Would be cool to be able to have those AI voice things that sound like celebs but i think thats a bit much to ask ha

Team•

Feb 26, 2025

This has been released to our beta test group in preview today.

Emerald Squash

•

Feb 6, 2025

Yes!!! I use AI for idea buidling and doing it by chat just really cuts down on my ability to generate good stuff. I use it more like a mirror and enhancer rather than a brain replacement and in that sense it’s really useful to have voice

Moccasin Meerkat

•

Feb 7, 2025

If Venice could talk as well as ChatGPTs Maple, that would be PERFECT!!!

Magenta Spring

•

Feb 7, 2025

yes please. This is my #1 workflow.. currently i am using chat gpt voice to text and then copying it and pasting into my venice ai models. .lol… i love this feature so much… it eventually will be a deciding factor for any that dont have this ability for me. But i know Venice is in early iterations and love what we have so far. :)

Yellow Toaster
•
Feb 14, 2025
Superwhisper and WhisprFlow are good hotkey apps for the voice to text bit.

Olive Sunbeam

•

Jan 27, 2025

This would be great, not only to create voices for any projects but also to select a voice, or have the AI do it, to either read out generated responses or character dialogue.

Currently using the windows magnifier read from here function on all text responses to achieve this. Having more TTS features available would help from an accessibility standpoint as accessibility functions are at times broken with updates to a site, browser, software itself or OS among other things.