#Strange behavior with Aura Asteria EN on the word: "message"

1 messages · Page 1 of 1 (latest)

west mantle
#

Good afternoon Deepgram team!

I've got some weird-ness with generating a TTS clip where Asteria is supposed to say "This is a repetitive message" but it ends up coming up with "This is a repetitive mess-" and cuts off without the "age" portion of the clip. I've attached some sample clips

  1. repetitive.mp3 - Should sound like "This is a repetitive message" requestId=8ddb7f7b-dbae-4fff-b6e8-0ca8626d2df4 (not sure about this one I only get character counts in the usage page so this one might be wrong)
  2. repetitive-wth-more-text - this one performs just fine, sounds great
  3. just-message.mp3 - Should say just "message" but really sounds strange. requestId=90c0df02-79d7-408d-a72d-fc177c814258
cold anchorBOT
#

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.
west mantle
#

This is the path + params I'm using: ```POST /v1/speak?model=aura-asteria-en&encoding=mp3

brazen plover
#

Thanks for this, and so much detail!

west mantle
#

Of course. I've had too many customers come my way with just: "hey there's a bug" so I hope this helps 🙂

fallow holly
#

Thanks @west mantle ! I've passed this one with the team to figure this out.

fallow holly
#

Btw @west mantle just talked to the team, I tried adding "." towards the end of the sentence

#

that should solve the problem for now while we figure out how to work on requests without a "."