Voice Broadcast Chip Solution: Text-to-Speech Conversion with Flexible Functionality

Voice broadcast chip solution, providing text content to voice conversion, functions can be single-wire, dual-wire, button, etc. The speaker can be directly pushed or an amplifier can be added. Development Considerations EMC Design The voice signal line must be grounded to avoid running parallel to high-frequency circuits. For direct push solutions, it is recommended that … Read more

Using the Base64 Command Tool in Linux to Restore MP3 Base64 Strings to MP3 Files

Using the Base64 Command Tool in Linux to Restore MP3 Base64 Strings to MP3 Files

Using the Base64 Command Tool in Linux to Restore MP3 Base64 Content to MP3 Files This article introduces how to use the base64 command line tool in Linux to restore a string of MP3 base64 to an MP3 file. Some TTS interfaces return audio content as base64 expressions In this case, we cannot directly know … Read more

Integrating Large Models in Embedded Systems: A Social Service Assistant Based on STM32 & ESP32

Integrating Large Models in Embedded Systems: A Social Service Assistant Based on STM32 & ESP32

1. Hardware Platform Selection and Modules 1. STM32 Solution Processor: STM32F407 / STM32H7 (high frequency, good performance) Peripheral Modules: WiFi Module: ESP8266 / ESP32-WROOM as the networking module Microphone Module: I2S MEMS microphone (e.g., INMP441) Speaker: I2S DAC + small speaker Display: TFT LCD (SPI/Parallel) Storage: SD card / external Flash (for caching voice data) … Read more

Meow Meow Practical Studio: Let Your Text ‘Speak’! Build a TTS Voice Synthesizer with Python and OpenAI API

Meow Meow Practical Studio: Let Your Text 'Speak'! Build a TTS Voice Synthesizer with Python and OpenAI API

Meow Meow Practical Studio: Let Your Text ‘Speak’! Build a TTS Voice Synthesizer with Python and OpenAI API <span>[Meow Meow Practical Studio #250802]</span> Author: AI Meow Intelligent Agent Hello, AI adventurers! Happy Friday! Welcome to this episode of <span>Meow Meow Practical Studio</span>! In previous practical projects, we have processed text and called tools using AI, … Read more

Update: MultiTTS Desktop Reading Plugin v1.2, Powerful Browser TTS Text-to-Speech Extension

Update: MultiTTS Desktop Reading Plugin v1.2, Powerful Browser TTS Text-to-Speech Extension

The MultiTTS desktop reading plugin has been updated primarily to fix bugs, and it is recommended to use the latest version. Installation is quite simple: remove the old version and reinstall it using the method previously introduced (remember to change the IP address after installation). Update Log 1. Added a paragraph word count option in … Read more

Recreating Xiao Zhi AI Step 2: Learning Its WebSocket Protocol Through Two Core Flowcharts

Recreating Xiao Zhi AI Step 2: Learning Its WebSocket Protocol Through Two Core Flowcharts

Introduction Continuing the attempt to recreate Xiao Zhi AI, but based on the Arduino framework. Last week, I completed the development environment setup for ESP32-S3 + ESP-SR + ESP-TTS using VSCode + PlatformIO + Arduino (see the article “Recreating Xiao Zhi AI, ESP32-S3 Building Arduino + ESP-SR + ESP-TTS Development Environment Pitfall Record”), and the … Read more

Recreating Xiao Zhi AI: A Journey Through Building an Arduino + ESP-SR + ESP-TTS Development Environment on ESP32-S3

Recreating Xiao Zhi AI: A Journey Through Building an Arduino + ESP-SR + ESP-TTS Development Environment on ESP32-S3

Recently, the Cyber Dog and Xiao Zhi AI have become quite popular on Bilibili. I also wanted to recreate one, preferably combining both, and after some research, I found that the authors’ open-source solutions did not quite match my preferences. I decided to modify them, which led me on a journey of troubleshooting. Reason The … Read more