AI-generated Answer for mas.o.menos
Currently, ElevenLabs' Text-to-Speech system focuses on generating speech based on textual input and does not support the direct generation of nonverbal sounds like "shhh" or "weh" as standalone phonemes. While the AI model is sensitive to the context of the text and can produce expressive speech, it may struggle with generating isolated nonverbal sounds or phonemes naturally.
For more nuanced vocalizations, such as laughter, sighs, or other nonverbal expressions, these features are highly requested, and the team is working on making them possible in the future. However, there is no specific timeline for when this functionality will be available.
If you have further questions or ideas, feel free to share!
bitter socket
bold crest