#Filler words

1 messages · Page 1 of 1 (latest)

hasty bison
#

I want to produce human like audio from deepgram, so i want to add filler words like um, ahh, er, aaaa, etc.

Is there any list of words that can be provided that can help me do that, as all the above mentioned example sound robotic and when i try to product sound for hmm i get this 400 error 'dg-error': 'Bad Request: Input is unutterable'

any suggestion on what can i use for this

here is a example "Umm, I was, er, thinking we could, umm, maybe go to the, aaah, new restaurant tonight because, umm, I heard they have, er, aaaa, really good food, aaah, if that sounds, umm, okay to you?"

is there a way to make it sound more natural

sonic saddleBOT
#

Thanks for asking your question. Please be sure to reply with as much detail as possible so we can assist you efficiently. Such as:

  • Provide the request_id if you've a question about a transcription response.
  • The options you used or the api.deepgram.com URL you sent your request to, including parameters.
  • Any code snippets you can include.
  • Any audio you can include, or if you can't share it here please email it to us at [email protected] and provide a link to this thread.
elder stump
hasty bison
#

i have already gone through this, but this doesn't help me except the ... for a breath like pause.

elder stump
#

A comma (,) or a period (.) present in your text will be treated as a very short pause.

opaque prairie
#

So instead of um, you'd inject , um,

elder stump
# opaque prairie So instead of `um`, you'd inject `, um, `

I believe so. The common mistake is to confuse normal puctuated sentences for a TTS prompt. Things like SSML exist, and other providers use their own styleguides. (I prefer SSLM). But users will have to use prompting to produce the sort of cadence and identity they want