snakers4 / silero-models

Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple
Other
4.86k stars 301 forks source link

Feature request - [Subtitle voiceover] #226

Open bropines opened 1 year ago

bropines commented 1 year ago

🚀 Feature

A simplified system that simply asks for srt and other types of sub files, and voices them by timings.

Pitch

I wanted it to be as simple as Whisper. That is: silero-tts --file oleg.srt --sample-rate 48000 --model olesya --lang ru

Alternatives

There are no alternatives on the Internet that can do this in Russian and relatively easy

dmki commented 1 month ago

If you are on Windows, you could use SoundWorks to generate Silero voiceover for SRT. I don't think it should be part of the engine itself to do such custom niche tasks. Third party apps that consume Silero might handle it better.

In fact, you could do it yourself.

bropines commented 1 month ago

When this question was asked, I did not understand anything in the documentation. Now, with experience, we should try again.