Tutorials: Voice Widget: Say/Play
Required access: Voxtelesys Portal
The Say/Play widget plays an audio file, says text-to-speech (TTS), or plays DTMF tones to the user. If playing an audio file, the URL must be publicly available and return an MP3 or WAV file. Additionally, the response Cache-Control header is honored if provided. To reduce latency caused by download times, it is recommended to provide the Cache-Control header. Once cached, the file will be locally retrieved until it becomes stale.
If playing DTMF tones, the tones will be injected into the call which can be useful when testing IVRs with a known call flow structure.
This widget converts text to speech (TTS) and plays back the generated audio to the user. Currently supported TTS engines include AWS. The call is billed for the length of the Text, in 100 character intervals. Pricing is dependent on the engine used for TTS synthesis.
You will want to place the answer call widget at the front of the flow if you plan on collecting input/directing the caller around.
*Disclaimer: You will need to have Voice API enabled on your account to do this you will need to open a ticket with support.
Last Updated: 1/16/25
To use the widget simply click and drag it into the builder
Note that naming the widget can help identify it with other tools later on. It is case sensitive, does not accept spaces or dashes
The Pause Call widget has the following configuration abilities:
Action Type
Say Text: This action will allow you to enter text and use our voice engine to play it for your customers
Play Audio: This action allows you to redirect the widget to a URL to play a message
Play Digits: The actions will say back the digits you specify (useful for confirming a caller input)
Say Text Action
Say Text
If you select the Say Text action then you will be prompted to enter in the message
Language
Select from our support languages
Voice
Select from our built-in voices
Enable Translation (optional)
Displays the options for translation. The text that will be translated is "Say Text"
Language Model (optional)
The type of translation model and vendor to use. Currently we only support Google as a vendor. Text is billed in 100 character intervals and pricing is based on the model selected.
- [Google] Large Language Model: use Google’s LLM to translate text. The LLM supports fewer language pairs than the NMT model, but large language models tend to generate more natural sounding translations.
- [Google] Neural Machine Translation: use Google’s NMT model. The NMT model supports many more language pairs, but may not be as natural sounding as a LLM.
Translate From (required if Language Model is selected)
The language to translate from. The input text should be typed in this language. Automatic language detection is only supported if the user chooses to use the NMT model.
Translate To (required if Language Model is selected)
The language to translate to.
Loop(s)
The number of times the text is repeated.
Play Audio Action
URL
The URL of the audio file to play to the caller.
Loop(s)
The number of times the text is repeated.
Play Digits Action
Digits
The DTMF tones to play during the call.
Loop(s)
The number of times the text is repeated.
Now, you will want to connect the Say/Play widget.
Adding the Say/Play widget is completed!
To continue the flow, connect more widgets to the opposite end of the Say/Play widget:
Now connect more widgets! Click on the links below to view more tutorials:
Voice
Messaging
Tools
Control
