Talkstack
  • System architecture
  • Getting Started With Talkstack's API
  • Authentication
    • Signup
    • Verify Email
    • Resend email verification code
    • Login
    • Refresh Token
    • Change Password
    • Forgot Password
    • Reset Password
  • User
    • Generate API key
    • Set active Project
    • Get active Project
  • Project
    • Creating a new project
    • Get Project
    • Getting list of projects
    • Update a project
    • Delete Project
    • Webhook
    • Get Active Agent
    • Set Active Agent
    • Remove Active Agent
  • Agent
    • Create a new Agent
    • Get Agent Details
    • Update Agent
    • Delete an agent
    • Get All agents
  • Call
    • Make phone call
    • Get call data
    • Get call history
    • Get call analysis
    • Batch calls
  • Voices
    • List Voices
    • Get Voice data
  • Phone Number
    • Get phone number data
    • Assign Number to Agent
  • Hubspot
    • HubSpot Integration
Powered by GitBook
On this page

System architecture

NextGetting Started With Talkstack's API

Last updated 4 months ago

Overview

Our architecture is designed to provide seamless integration and efficient processing of client requests through our Talkstack AI system. Below is a detailed overview of the components involved and the workflow.

Workflow Description

  1. Client Requests: Clients interact with our system by sending RESTful API requests (GET/POST/PUT/DELETE) to our endpoints. These APIs are hosted on Microsoft Azure, ensuring high availability and reliability. While we typically host our API and MongoDB in the US, we have the flexibility to deploy in locations preferred by our customers.

  2. API Processing: Upon receiving the client requests, our API layer processes the requests. This layer interfaces with a MongoDB instance for any necessary data storage and retrieval.

  3. Speech Processing:

    • Automatic Speech Recognition (ASR): The initial step in the call handling process is ASR, where the client's spoken input is converted into text.

    • Talkstack LLM: The text output from the ASR is then processed by our Talkstack Large Language Model (LLM). This AI component generates appropriate responses based on the input.

    • Text-to-Speech (TTS): The generated text response is then converted back into speech using TTS technology, providing a vocal response to the client.

  4. Call Routing: The entire process of ASR to TTS is part of the Talkstack calls component, with calls routed efficiently by Twilio to ensure smooth communication.

This architecture ensures that our system can handle client interactions effectively, providing accurate and timely responses using advanced AI and cloud technologies.

Architecture diagram