Closed Dragoy closed 8 months ago
Or have support for the prosody
tag in SSML:
`<?xml version="1.0"?>
<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://www.w3.org/2001/10/synthesis
http://www.w3.org/TR/speech-synthesis/synthesis.xsd"
xml:lang="en-US">
</speak>`
This tool is ideal for converting .srt to ssml format: https://github.com/ThioJoe/SRT-To-SSML
Now, unfortunately, this format does not work and causes an error:
Yes, I will continue working on this format, however Bark is not the best for exact tts, as every result can be quite different and speech breaks are more or less random. Do you know if one could add custom metadata (like Seedvalue) to the SRT-STandard?
Support for .srt It would be cool to have support for .srt format as text, which would be voiced depending on the timings.