Instead of recording in english (AI speaker) I would like to insert a recorded voice file to use as an AI speaker in spanish. I am a native spanish speaker.

hello im kurdish kurmanji teacher at university in kurdish department. Kurdish language is 50 million peopla language. so it is very needed to transcript feature for kurdish. Still anybody didnt create this text to speech or speech to text in kurdish. so it is very important for everybody and every company. please add kurdish kurmanji language to your system. I can help you for this with other teachers if you create system for kurdish.

It appears to be difficult to find functional solutions for this (transliteration but also pronounciation and text-to-speech generation). We knew, that a directive dating back some years existed, to explore and envolve these localizations into services for Speech recognition and Speech synthesis. Thankful for any contactation on these issues. Many thanks in advance ; be well, all good wishes to you.

Please make it possible to also select the language specific stock voices for generating speech. Optionlally the basic language of a project should be selectable (not only english) and this could trigger making the recommended AI stock voices of that language available for use.

For example, when generating Dutch texts, the currently available stock voices unfortunately all generate speech with English accents. However, when translating and dubbing Enlish text to Dutch, it's possible to select the voice 'Sem', which works excellent in Dutch. It should be possible to also select Sem (and the other language specific voices available when dubbing) in the standard list of stock voices for generating text in the first place. Now I need to generate the text twice (once in bad dutch and once with dubbing), doubling the use of the scarcely available speech generation and dubbing time...

This solution should be quite straightforward to implement...

I would like to see support for complete training in Portuguese (Brazil). I want to create YouTube videos by converting text into speech using my voice in Portuguese (Brazil) through your Avatar feature. However, the current Portuguese (Brazil) Avatars, both male and female, have a very robotic voice, and the accent is not very natural.

My podcast guests only speak german and I cannot record in descript because all the setting stuff needs to be set up in English at the moment.

In the text-to-speech feature, there's no way to specify the source language and the accent of the speaker. It makes a big different in Portuguese where Brazilian and Portuguese accents are quite different. Frustratingly, the Underlord AI stubbornly claims it's able to change this, but then it doesn't actually change anything in the generated audio.

When will overdub in foreign languages be available?