I never thaught I'd be saying this, but processing #XML from #C to turn #XHTML into #SSML with #libxml2 was an utterly *enjoyable* experience! I know right, in what universe is that possible? But props go to Daniel Veillard, Gnome, and contributors. It's fast, simple, and easy to understand, and everything just worked!

Using #GPT for #voice #TTS #NLG, with #SSML?
Some smarter usage examples:

1. ask GPT to create the SSML from a text requiring a given a tone (e.g. positive)

2. ask GPT to assign itself the tone, dynamically in relation of the contextual meaning of each sentence (to be improved)

original post: https://twitter.com/solyarisoftware/status/1610317686029881349?s=20&t=Lf9GbgRvOQvRB03pKCR1RA

We’re looking for people interested in technical solutions to text-to-speech (TTS) synthesis pronunciation 🔉 Please review requirements in updated Drafts.
See questions in email https://lists.w3.org/Archives/Public/public-wai-announce/2020AprJun/0002.html
For background, see https://www.w3.org/WAI/pronunciation/
#a11y #TTS #pronunciation #SSML

RT @LeonieWatson

Working on some demos and examples for a new talk on ways to make artificial speech sound more human #VoiceXML #SSML #WebSpeechAPI #CSSSpeech (one day)

🐦🔗: https://twitter.com/LeonieWatson/status/1106948269270278147