You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'd love to have direct support for Amazon Polly. It's TTS engine is so much better than the currnetly implemented one. It allows for changing voice, pitch, volume and emphasis mid-sentence and the quality is so high that you could actually use it in a finished book/game.
Also, it has a very generous trial period (I think you get 5 million free characters per month for a year). After that it costs $4 per 1 million characters.
I am not too eager to deeply integrate a proprietary service directly into tttool. And the TTS support is only meant as a development aid anyways… But it should be possible for you to create a separate tool that creates the media files, and even supports the extra options etc?
Ah, I see you did that already. Since it's a separate file anyways, how about you turn this into its own tool and project? We can link it so that people can find it, without confusing tttool users about why they need python or AWS credentials etc.
I'd love to have direct support for Amazon Polly. It's TTS engine is so much better than the currnetly implemented one. It allows for changing voice, pitch, volume and emphasis mid-sentence and the quality is so high that you could actually use it in a finished book/game.
Also, it has a very generous trial period (I think you get 5 million free characters per month for a year). After that it costs $4 per 1 million characters.
The API is rather simple, and there is a Haskell package that handles about everything you need to use Polly here: https://hackage.haskell.org/package/amazonka-polly
I would implement it, but I have had my fill of Haskell ;)
The text was updated successfully, but these errors were encountered: