2 Answers
- Newest
- Most votes
- Most comments
0
I am sure you can do it, but not sure you will want to. Here's how I see this happening:
- Identify what you want to say and create string "Hello and thank you for calling.."
- Have Lambda send this string to Google to generate an audio file, which will then get pushed to an S3 bucket, which will then provide you with an ARN.
- Save ARN location as an attribute.
- Play ARN location in Connect.
This feels like unnecessary steps which might cause delays in your flow and not a great customer experience. If your prompts are pretty static could you just generate them all in Google and then put them in an S3 and only use Polly for dynamic information, like dates or values?
answered a year ago
0
You cannot replace the native TTS engine (AWS Polly) in Amazon Connect.
As mentioned, best bet is to use Play Prompt from S3 feature so you can update the prompts dynamically built from other TTS engine to those locations as needed
answered a year ago
Relevant content
- asked 3 years ago
- asked 3 months ago
- AWS OFFICIALUpdated 2 months ago
- AWS OFFICIALUpdated 2 years ago
- AWS OFFICIALUpdated 5 months ago