i just want to know can we take input in IVR through voice without lex in amazon connect. If yes So, How?
AWS Connect does not have Speech-To-Text capability on its own. It uses Lex for that.
So without using Lex, Connect can only operate like the old automatic phone operators using the DTMF (number keypad input).
Related
I want to Integrate Audio Voice Change into Twilio Voice Call Steps and Questions
Call Rest API for an introductory call from one device to another
Now how to implement a Voice changer in-between a Call?
For Changing Voice I would re-commend Aroga Voice changer Functionality
Now How to provide Agora voice changer output to Twilio Input?
Most Importantly How can we Connect two Functionalities with Each Other? #TwilioHelp #TwilioSupport
I want to Modify outgoing Voice Call input and Pass towards the End Call
How am I Gonna do that?
Firstly, I'll Make call Streams using Web-sockets, SO that I can get a input Stream from User
Then-after I can Modify the Voice according to Users Perspective
First question -> Is this possible? to get Voice from Stream?
I'll use Some Voice Algorithm and the Out-put of that Algorithm will be Redirect to Twilio Voice, So that the End User can Listen the Modified Voice!
Please Help me to Implement this Functionality!
Thanks in Advance and regards
We need a possibility also to identify DTMFs.
Scenario:
On a phone conversation we ask the user "Please enter id number".
We stream the audio to google cloud speech to text.
We would like to support both options at the same time: (a) user says the id nubmer (b) user presses the id numbers using phone keys (DTMf).
DTMF seems can't be detected using Cloud Speech-to-Text. I've opened a public issue on your behalf requesting this feature. You can star the issue and follow the progress.
As a workaround you can use scipy.signal library's spectogram method to detect the unique DTMF frequencies.
Twilio not detecting my DTMF tones from Skype.
We have setup an IVR system with twilio whereby clients must enter a
7 digit client number.
Some of our clients phone from voip phones,
therefore we need to ensure that twilio can detect the DTMF tones
properly (most use Skype so that is our primary concern right now).
Twilio IVR detects tones fine from mobile or landline phones.
Calling other IVR systems from our Skype clients works just fine
Entered a support case w/ Twilio but so far they have not been helpful so I'd like to poll the StackOverflow community.
Versions of Skype tested (at various different physical locations):
Skype version 7.4.0.104 on Windows 8
Skype version 8.11.0.4 on MAC OSX Sierra
To make matters more confusing for us, about 20% of the calls that we make via Skype it DOES accept the tones. The other 80% of the time the calls are not recognizing the tones.
We believe this to be a problem with either Twilio accepting DTMF tones from voip phones OR something that is running inconsistently in our Twilio scripting. Because we can dial other IVR systems and enter codes fine with Skype, it doesn't appear to be a problem with Skype.
In our TwiML voice scripting we are using GATHER. Here is a sample of our gather code:
<?xml version="1.0" encoding="UTF-8"?>
<Response>
<Gather action="clientcode.jsp" timeout="15">
<Say>Please enter your client code.</Say>
</Gather>
<Redirect method="GET">gatherfields.jsp</Redirect>
</Response>
Any advice or direction to point us in is helpful.
I had the same issue for several months. After a laborious but fruitful exchange with Skype Support (Virtual Assistant, subsequent email exchanges with several Skype Support people, Remote Desktop Control, etc!) the support team eventually figured out that there is an issue with the Subtitles Function. They have now updated the FAQ here:
https://support.skype.com/en/faq/FA34713/faq-and-known-issues-with-skype
When making a call and using the Dial Pad to select the option for Touch Tones, they will not work if you have subtitles enabled on the call.
To workaround this issue simply disable subtitles: Select your profile picture > Settings > Calling > Call Subtitles, then turn off the option to Show subtitles for all voice and video calls.
Note: If you don't have the option turned on to Show subtitles for all voice and video calls but have turned subtitles on for an individual call, starting a new call with your contact will resolve this issue.
Also, when you are using the iOS Skype app to test this, open the app and do the DTMF in the Skype app's keypad. Don't use the iOS default call, it won't work.
Using the IBM Watson Speech-to-Text add-on for Twilio it makes me configure a callback url in the add-on configure tab.
Now my issue is how do I get this to only affect ONE phone number? or a specific TwiML? I cannot have all going through the add-on.
Example:
phone number 1 -> goes to some other webhook
phone number 2 -> uses TwiML bin with <Record> // I want this one to be transcribed by the IBM add-on
Should I rather have #2 hit a webhook which uses the IBM SDK and returns a record response? (if such a thing exists)
Twilio developer evangelist here.
I'm afraid Add-ons currently work on all your numbers on an account level right now. Can I suggest a work around that you start a subaccount and enable the Add-on for just the subaccount. Then move your number that you want to use for recording and transcribing to that subaccount.
We use microsoft botframework for our chatbots. We would want to enable Voice channel to our bot. Is there a way to solution this? Does Twilio have anything that can add speech capabilities to our bot. Our bots are exposed via webchat components, skype, facebook messenger etc.
Twilio developer evangelist here.
There's no way within Botframework to add voice capabilities from Twilio, however receiving calls works in a similar way. When someone calls your Twilio number you receive a webhook which you can respond to with TwiML to tell Twilio what to do with the call.
To then perform things by voice action you can <Record> the caller's response and set the transcribe parameter to true. You also need to set a transcribeCallback URL as the transcription is done asynchronously. Once you receive that callback, the text of the transcription will be available as a parameter in the request. You could also perform the transcription yourself with a third party service by just taking the recording and sending it off.
Once you receive the transcription you can then make your decision as the the next step of the conversation and redirect the live call to the next step of your process using the REST API.
This is just a high level overview of how you might accomplish this. Let me know if it is of any help.
Voximal offers as Twillo a similar product but based on VoiceXML. The difference is that Voximal integrates natively most of STT engines (Microsoft, Google, Watson, iSpeech) in the solution (you only need to set the key or the user/password to configure them). You use a builtin grammar "text" to translate. Then the processing is very similar to the Twilio. You need to push the content to a chatbot engine (HTTP/XML/JSON), and you have a way to play the result with a TTS engine.
Have a look to the Parrot example (a script that repeats all you said using the STT and TTS) :
https://github.com/voximal/voicexml-examples/blob/master/parrot/parrot.vxml