Asterisk Developer - PBX - AWS Transcribe
- or -
Post a project like this£231(approx. $290)
- Posted:
- Proposals: 1
- Remote
- #2394585
- OPPORTUNITY
- Expired
Description
Experience Level: Expert
Background
Kylar is a conversational voice bot that makes outbound calls and has a conversation with the callee using Artificial Intelligence. Kylar already exists and is working with Twilio’s Programmable Voice service. We are running on AWS.
Purpose
We have hit a number of road blocks with Twilio that mean we have to look at bringing the technology in house to give us more control.
Work to be done
Scaling
Ultimately we need to be able to scale the outbound calling infinitely. Given there may be multiple servers, we would need to ensure
Speech-to-Text
We need to be able to stream the audio of the person being called (callee) to AWS via their Transcribe service. In time we may need to use other STT libraries.
Call Handling
Like Twilio, our app will need to communicate with this solution via REST calls and Callbacks.
Store WAV (for playing later)
Connect Salesperson (initially via WebRTC)
Start Call (number to dial, call ID)
Status Callback (ringing, connected, disconnected, failed + ID)
Leg Callback (this is when the person finishes speaking and we pass back the text, we then return with which WAV file to play - passing ID)
Merge call (outbound to salesperson)
Hangup call
Get Call Recording
Get Call Report (length, who to etc)
Get System Status (current call numbers etc)
Play Background Noise
Ability to choose a WAV file stored locally to play during the call
Kylar is a conversational voice bot that makes outbound calls and has a conversation with the callee using Artificial Intelligence. Kylar already exists and is working with Twilio’s Programmable Voice service. We are running on AWS.
Purpose
We have hit a number of road blocks with Twilio that mean we have to look at bringing the technology in house to give us more control.
Work to be done
Scaling
Ultimately we need to be able to scale the outbound calling infinitely. Given there may be multiple servers, we would need to ensure
Speech-to-Text
We need to be able to stream the audio of the person being called (callee) to AWS via their Transcribe service. In time we may need to use other STT libraries.
Call Handling
Like Twilio, our app will need to communicate with this solution via REST calls and Callbacks.
Store WAV (for playing later)
Connect Salesperson (initially via WebRTC)
Start Call (number to dial, call ID)
Status Callback (ringing, connected, disconnected, failed + ID)
Leg Callback (this is when the person finishes speaking and we pass back the text, we then return with which WAV file to play - passing ID)
Merge call (outbound to salesperson)
Hangup call
Get Call Recording
Get Call Report (length, who to etc)
Get System Status (current call numbers etc)
Play Background Noise
Ability to choose a WAV file stored locally to play during the call
Matthew D.
100% (1)Projects Completed
1
Freelancers worked with
1
Projects awarded
6%
Last project
10 May 2019
United Kingdom
New Proposal
Login to your account and send a proposal now to get this project.
Log inClarification Board Ask a Question
-
There are no clarification messages.
We collect cookies to enable the proper functioning and security of our website, and to enhance your experience. By clicking on 'Accept All Cookies', you consent to the use of these cookies. You can change your 'Cookies Settings' at any time. For more information, please read ourCookie Policy
Cookie Settings
Accept All Cookies