Showing results for 
Search instead for 
Did you mean: 

UCCX Prompts

Is there anyway to create automated prompts like these and use them in UCCX?  I have attempted to do this and corrected the settings in Audacity however, when the prompts play they are extremely garbled and cannot be understood.  I figured it would be nice to use text to speech and create these.


Accepted Solutions

I found out what the issue was.  I had to set the project to 8000 and use "Tracks > Resample" before exporting.  Once I did that everything sounds normal.  Thank you for your help and pointing out all of these various resources and guides.

View solution in original post

Chris Deren
Hall of Fame Master

As long as you save them with proper audio settings it does not matter where you get the prompts from. Assuming your UCCX is using G711 codec you need to save the file with following settings:

  • Format: CCIT U-Law
  • Sample Size: 8-bit
  • Sample Rate: 8kHz

Here is good blog:

Hi Chris,
I use Audacity and review the link you provided. All my prompts have been done with Audacity for quite a long time. I wanted to take one of the existing prompts playing in UCCX and revise it some (take out some long pauses, etc), clicked on the prompt in UCCX Prompt Mgr and I get a pop to open it in Audacity, which I do (choose copy so I dont mess with what is in Uccx until I am ready).
The settings are the same 8000 hz ; ULAW, .WAV ... , I then upload it using the upload function in Prompt Mgr. Update the application that uses the prompt, and I get garbel sounds. You post indicated 8-bit format - but that is not available in Audacity ver I have (newer version), and the netcraftsman (url you provided) - in his examples it shows 32 bit - which is what mine are set to.
1) any other suggestions - I am on UCCX 11.6.1
2) any way to move a prompt from one folder to another or copy into another folder ? (another scenario going on with this)

Prompt should be in 8 bit, 8 KHz, mono, u-law format.

Other wise, you will hear a bad sound.


Are you looking to move the prompt from one folder to another in Prompt Management?

James Hawkins

I use Cisco Tropo to do this.

A developer account is free and you can write simple scripts to record calls and store the results on an ftp server. Tropo supports various languages - the script below is Python. When the application associated with it is called it plays a welcome message, then plays and records to sample prompts and transfers the recordings to an ftp server (in this case drivehq which is free) and then plays a goodbye prompt and hangs up.


say("Welcome to Tropo James")
say("Thank you for calling Example Company. Please select from the following options. For Sales press 1. For support press 2. For Customer Services press 3.", {"voice":"kate"} )
say("Thank you for calling Example company. Our office hours are Monday to Friday 8 a m to 5 p m. Please call back within these hours.", {"voice":"kate"} )
say("Goodbye James")


Free developer accounts do not have DDI numbers but do have SIP URIs that can be called using a Windows SIP softphone and free SIP account.


The recordings can be downloaded from the FTP server using something like Filezilla. They are not in G711 format so I use NCH Switch to convert them.


Trop offers lots of different voices and the prompts are pretty good quality.

This may sound complex but it is actually pretty simple.

I am currently writing a Python script which will automatically generate a Tropo python script from a CSV file containing prompt text, prompt names and voices.

Hope this helps


James, I dont think you can sign up for free Tropo account anymore.

Hi Chris,

It does look like you can still apply for a free Tropo developer account at the link below:

They do seem to be asking for a lot more information than was the case when I signed up though.

I guess that your application will be reviewed and could be refused if they do not think that there is a sensible use case and generating prompts for UCCX probably would not make the cut.


VIP Advocate

I'm not sure I understand your use case completely. Are you trying to do TTS in your IVR, like to read back a balance or a street address? Or do you want to be able to record new prompts using TTS and then upload them to UCCX?


For the first, UCCX offers some basic TTS-like functionality for numbers and dates, for more advanced stuff like reading back a status or some phrase you can use Nuance. For the second, the Tropo approach is what I would do, but not use Tropo. Amazon, Google, and Microsoft all offer pretty cheap TTS services. Here's some code which takes a CSV and produces MP3s using Amazon Polly. I haven't touched this code in over a year and I slapped it together when I had to do a few hundred prompts quickly, so please don't judge it too hard.


// Load the SDK
const AWS = require('aws-sdk')
var fs = require('fs')
var csv = require('fast-csv');

// Create an Polly client
const Polly = new AWS.Polly({
    signatureVersion: 'v4',
    region: 'us-east-1'

//                console.log(data[1]);

	let params = {
 	   'Text': data[1],
	    'OutputFormat': 'mp3',
	    'VoiceId': 'Kimberly'
	Polly.synthesizeSpeech(params, (err, stuff)=>{
		if (err){
		} else if (stuff){
			if(stuff.AudioStream instanceof Buffer) {
				fs.writeFile("./"+data[0]+".mp3", stuff.AudioStream, function(err){
						return console.log(err)
					console.log(data[0]+".mp3 "+"File was saved");




You are hearing the prompts as garbled because of incorrect format.
I used to make test prompts from, change the format and it used to work fine.
Make sure you are converting the prompt to wav file with 8 KHz, 8 Bit, Mono, u-law format

I found out what the issue was.  I had to set the project to 8000 and use "Tracks > Resample" before exporting.  Once I did that everything sounds normal.  Thank you for your help and pointing out all of these various resources and guides.

View solution in original post

Recognize Your Peers
Content for Community-Ad