edge-tts

Checkout https://github.com/rany2/edge-tts , which exposes it as a Python library and a CLI tool.

There is a MIT license in the repo. In that sense it's open source. It's using "Edge TTS", which I believe means using API keys [1] stolen from Microsoft Edge and hoping Microsoft doesn't sue you, non jolly-roger flying internet users beware. Can't speak to other models and their licenses, I stopped looking after I saw edge-tts since I don't feel the need to use this. [1] https://github.com/rany2/edge-tts/blob/ac41fb85ab2b2b48fef8a...

It's worth noting that there have been occasions where the library was blocked and it took a few weeks to workaround said block. For example, when a valid Sec-MS-Token became required, it took a while to implement it in the library: https://github.com/rany2/edge-tts/blob/08b10b931db3f788a506c... Basically, it's a very bad idea to use this library for anything serious/mission critical. It also is really limited to only taking in text (i.e., no custom SSML, emotion elements, etc) as Microsoft restricts the API to only the features Microsoft Edge itself already supports. Generally commercial users would want these more advanced features and so they'd want to use Azure Cognitive Services. At any rate this library was never really marketed, I'm not sure how it blew up. It was really only intended so that I can have audio files I can play back

They have locked down these APIs slightly but it's not a very complex "DRM" mechanism: https://github.com/rany2/edge-tts/blob/08b10b931db3f788a506c...

I've converted a few fan fictions into audiobooks using edge-tts (https://github.com/rany2/edge-tts). It uses a reverse engineered API from MS Edge to use the more premium MS voices for free. A bit of a grey area, but it works remarkably well.