Feature Requests

Hello, I’d like to kindly request help to test the new voice cloning features. At the moment, the multilingual functionality in Italian doesn’t seem to work very well. In text-to-speech, the voices sound somewhat unnatural and uncertain, often missing the intended tone and emphasis in many passages. Because of this, I’m hesitant to start a paid subscription before verifying that the output is actually usable. I’m currently a subscriber to ElevenLabs, which performs excellently for my needs, but I’m always open to exploring new and potentially better solutions. That said, I already spend quite a lot on various subscriptions, and I’d prefer not to risk wasting money just to test a service. Would it be possible for you to help with this? For example, by unlocking my cloned voice for testing, adding some credits, or activating the necessary subscription tier for one month? Please let me know if that’s something you could do. Thank you very much for your time and assistance! Best regards,

It's very strange and poor UX that you have to apply settings to each block of text within a chapter... if you want to say have the whole chapter be at 0.85 speed with a custom setting.., you have to go block by block applying it

Trying to re-generate or generate text, and it is randomly failing on certain sentences and will not make it through an entire chapter using the project's feature and octave 1 or 2. I have wasted over 10k credits since the update.

Some unfamiliar words are pronounced incorrectly by EVI-3 voices pronounce incorrectly, such as brand names of prescription drugs. It would be nice to have a dictionary to which developers can add entries that describe the correct pronunciation of these words using linguistic phonetic symbolic representations such as ARPAbet + CMUdict for English or IPA for International.

Ability to input a recording of one voice and have Hume output another voice (with the same timing characteristics). It would be great to use in an ai avatar workflow where the generated video should retain a real person's voice.

In the Christmas Lighting hobby, we stand up Mega trees that talk to the crowd and if you have more than one tree, talk to one another. To make it more real, allowing the two AI voices to overlap in a conversation would make the mega trees more real and life-like.

This would be useful for telephony.