LeeBoonstra.dev
Building Your Own Conversational Voice AI Which Streams Audio From a Browser Microphone to a Server (Part II)

Blog: Learn Machine Learning from a Google AI Engineer

Building Your Own Conversational Voice AI Which Streams Audio From a Browser Microphone to a Server (Part II)

This is the second blog in the series:
A best practice for streaming audio from a browser microphone to Dialogflow & Google Cloud Speech To Text.

In this first blog, I have introduced all the conversational components, and I addressed why customers would integrate their own conversational AI compared to building for the Google Assistant.

Today, I will make a start by building a client-side web application which uses a HTML5 Microphone with WebRTC, streaming the audio bytes to a Node.js backend.

Building Your Own Conversational Voice AI With Dialogflow & Speech to Text in Web Apps. (Part I)

This is the first blog in the series: A best practice for streaming audio from a browser micropho...
Orchestrate Multiple Sub Chatbots From One Chat Interface by Using the Mega Agent Feature in Dialogflow

Dialogflow has the Mega Agent feature. (At the time of writing, this feature is still in beta but...
Create High-Quality Chatbots by Making Use of Agent Validation, an Out of the Box Review Feature.

Dialogflow provides a validation feature. Agent validation results are available automatically wh...
Mastering Auto Speech Adaptation in Dialogflow for Voice Agents

Auto speech adaptation improves the speech recognition accuracy of your Dialogflow voice agent by...
Disclaimer: The opinions stated here are my own, not those of my company. - 2025 ® Lee Boonstra