thelamapi

/

neuvoice

like 6

Follow

Lamapi 13

Unfortunately, the user interface is currently under development, but we’ll have a basic version ready and published within two days. Thank you!

We will respond here once we’ve published it. Thank you very much.

thanks.

Unfortunately, the user interface is currently under development, but we’ll have a basic version ready and published within two days. Thank you!

We will respond here once we’ve published it. Thank you very much.

Are there any plans to develop this app so that it can recognise emotions and intonation?

For now, we already have a basic emotion system in place, you can try it out with tags like <breath> and <laugh>.

Of course, we are also considering developing a version of this model that includes more parameters. Thank you very much for your feedback and support regarding the model.

For now, we already have a basic emotion system in place, you can try it out with tags like <breath> and <laugh>.

Of course, we are also considering developing a version of this model that includes more parameters. Thank you very much for your feedback and support regarding the model.

Are there any others besides happy>, laugh>, breath>, and sad>?

Is this really how you use it?

Yes, that's how it's used, and there's another one like <sigh>, but it can cause issues with some sound styles; things like <breath> and <laugh> work more reliably.

We truly appreciate your interest.

Leon, Lina and Mustafa have no emoticons

Sharp, only some emoticons.

Alina and a few others are still reading the text in "<...>"

Using multiple emoticons in a text helps maintain consistency. Thank you for your support and feedback.

Using multiple emoticons in a text helps maintain consistency. Thank you for your support and feedback.

what do you mean "using multiple emoticons"?

Let me give you one of the examples from the explanation: If you use multiple expression tags this way, you can get more accurate results.

style = tts.get_voice_style("Lina")
text = "Good news! <breath> We just shipped the feature. <laugh> Don't tell anyone yet."
wav, dur = tts.synthesize(text, voice_style=style, lang="en")