#How do I make it so my model shows human emotion. For instance chuckling while saying something lik
1 messages · Page 1 of 1 (latest)
To make your model produce emotions, you need to consider a few things:
-
Context is key for generating specific emotions. Thus, if you want a chuckling or amused output, you might want to input text that sets a humorous or light-hearted context.
-
Punctuation and voice settings play a significant role in how the output is delivered.
-
You can add emphasis by putting the relevant words/phrases in quotation marks.
-
If you're generating speech using a cloned voice, the speaking style contained in the samples you upload for cloning is replicated in the output. So if the speech in the uploaded sample is monotone, the model will struggle to produce expressive output.
However, these tips do not guarantee the result. The AI is currently working on introducing features that will allow for the control of emotions within the text.
If you want the AI to express a specific emotion, the best approach is to write in a style similar to that of a book. For instance, you can use dialogue tags to express emotions, such as he said, chuckling, or he said with a chuckle. These types of prompts will help the AI understand the desired emotional tone and try to generate a voiceover that accurately reflects it.
Here's an example:
"Oh really?" he said, chuckling.
Remember, the AI will read exactly what you give it, so you'll need to somehow remove the prompt. The AI can also sometimes infer the intended emotion from the text’s context, even without the use of tags.
Well, wait a second. Your API provides a Text to Speech With Timestamps; couldn't I use that to detect when a specificy substring of characters is identified?