Speech Recognition

Automatic Speech Recognition (ASR) is a software solution developed by CPQD for automatically converting speech to text, allowing the most diverse applications to use speech for input.

Tip

NEW FEATURE: Number, date, currency, time and percentage formatting (tutorial).

• Getting Started
  • Speech Recognition
  • Product Overview
  • Feature Summary
  • Developing Applications
• Installation
  • Main Components
  • System Directories
  • System Requirements
  • ASR License
  • Installing the components
  • Install via script
  • Verify the Installation
  • Start Server
  • Test Server
  • Stop Server
  • Restart Server
  • Start when Machine is Booted
  • Restart after Error
  • Load Balancing
• Configuration
  • How to configure?
  • Recognition
  • Speech Detection
  • License
  • ASR Engine Logging
  • ASR Server Logging
  • Tuning Log
  • WebSocket Timeout
• System Logs
  • The Service Log
  • Server Log
  • Recognition Log
• Monitoring
  • Health Check API
  • Metrics API
• User Guide
  • First Steps
  • Integration with the ASR
  • Input Audio
  • Using Free Speech
  • Using Classifiers
  • Using Grammars
  • Continuous Mode
  • Text Formatting
  • Writing Grammars
• WebSocket API
  • Protocol
  • Access
  • Messages
  • WebSocket Codes
  • Asynchronous Mode
• REST API
  • Protocol
  • Access
  • Methods
  • Continuous mode
• GRPC API
  • Protocol
  • Access
  • Asynchronous Mode
  • Synchronous Mode
• MRCP API
• Error Codes
• Terms and Definitions
• Release Notes
  • 3.1.0, May 2023
  • Changes in Previous Versions
• Models Release
  • Brazilian Portuguese
  • Spanish
  • English