Expressions and Tonality [Overdub]
under consideration
Marquis Miller
Just in case, but so far cant tell while it's in dub: We need to include having exclamations, capitalization, question marks, etc, have their own recorded inputs/outputs.
Or at least highlight what you want to have expression/tonality and test around the attitude of a sentence or word.
Laura Burkhauser
under consideration
J
Jeanne Boles
How do we vote?
Laura Burkhauser
in development
G
Gerry MacPherson
I would really like to see a way for the speech to recognise question and exclamation marks in my overdub. I feel it would enhance the program.
M
Matty Dalrymple
Yes! This!! And a rising or falling intonation at the end of a sentence shouldn't be based just on punctuation--for example, you'd want questions that suggest a yes/no answer (e.g., "Are you going out?") to rise but questions that do NOT suggest a yes/no answer (e.g., "Where are you going?") to fall.
Frameworks
Concerning your request, I have voted for it and am recommending the use of Speech Synthesis Markup Language (SSML) tags to provide additional control over how Overdub generates speech from the text. Please see (and up vote :) my request entitled "Provide additional control over how Overdub generates speech from the text (e.g., using SSML tags) here: https://feedback.descript.com/feature-requests/p/provide-additional-control-over-how-overdub-generates-speech-from-the-text-eg-us
USE-CASES
- Amazon's Alexa: https://developer.amazon.com/en-US/docs/alexa/custom-skills/speech-synthesis-markup-language-ssml-reference.html#ssml-supported
- Google's Assistant: https://cloud.google.com/text-to-speech/docs/ssml
- Siri, et al: https://www.smashingmagazine.com/2019/03/sanity-portabletext-speech-synthesis/
Frameworks
+100 for this. While Descript automatically handles normal punctuation, such as pausing after a period, presently it does not appear to raise pitch when speaking a sentence ending in a question mark (i.e., it must raise pitch to indicate a question and prompt a response; instead, it appears to maintain pitch as if speaking a simple statement).
Alessandro
+1 for this, we're also experiencing the need to have this feature. We believe it would make stock Overdub voices sound much more natural.