#speech-to-text
118 related articles
Moonshine: A Low-Latency Speech Engine…
·2 min
Moonshine: A Low-Latency Speech Engine and Open-Source Powerhouse for Building Voice Agents
Moonshine is an open-source, C++-based low-latency speech engine combining STT, intent recognition, and TTS for building voice agents. 9,400+ GitHub Stars.
Read more →
transcribe.cpp: A Unified Speech Recog…
·2 min
transcribe.cpp: A Unified Speech Recognition Engine Built on ggml, Supporting 16+ Model Families
transcribe.cpp is an open-source ggml-based speech recognition engine supporting 16+ model families in a single C++ codebase — lightweight, cross-platform, and quantization-ready for local STT.
Read more →
Self-Hosted Voice AI Assistant: Bringi…
·2 min
Self-Hosted Voice AI Assistant: Bringing Conversational Intelligence to Asterisk/FreePBX
Explore a self-hosted voice AI assistant built for Asterisk and FreePBX: keep data on-premises, integrate with existing PBX, replace legacy IVR, and deploy local voice intelligence affordably.
Read more →
GitHub Daily · July 20: AI Agent Infra…
·3 min
GitHub Daily · July 20: AI Agent Infrastructure Explodes Across the Board
AI Agent infrastructure explodes across GitHub Trending: OmniRoute unifies 268+ providers, cognee adds long-term memory, and self-hosted openship tops growth with +1719 stars.
Read more →
·3 min
AI Second Brain Tech Stack: Building a Proactive Intelligent Assistant for ADHD Users
How to build a true AI second brain for ADHD users: LangGraph, n8n, RAG, vector databases, and layered architecture for a proactive personal assistant.
Read more →
·2 min
Leaving Perplexity Pro After Two Years: How to Export Your Data and Find the Right Alternative
A 2-year Perplexity Pro user explains why they're leaving. Covers how to export chat history in JSON/PDF/Excel, and compares Google Gemini, ChatGPT, and Claude as alternatives.
Read more →
·3 min
GPT-Live Hands-On: Voice Finally Gets GPT-5.5 — How Good Is the Full-Duplex Experience?
GPT-Live hands-on: Voice chat now powered by GPT-5.5 Thinking, full-duplex architecture, real-time search, visual cards & tool calling. Full review inside.
Read more →
·2 min
ChatGPT's New Voice Mode: Full Duplex Conversation, Real-Time Reasoning, and Live Translation Explained
OpenAI's GPT Live One powers a new ChatGPT voice mode with full duplex conversation, real-time web reasoning, and live translation. Here's a deep dive into all three breakthroughs.
Read more →
Apple SpeechAnalyzer vs Whisper: Speed…
·2 min
Apple SpeechAnalyzer vs Whisper: Speed, Accuracy, and Privacy — A Comprehensive Comparison
Apple's WWDC 2025 SpeechAnalyzer API runs fully on-device with zero latency and no cost. We compare it against OpenAI Whisper on accuracy, speed, privacy, and cross-platform support.
Read more →
·2 min
Complete Spring AI Tutorial: ChatModel, RAG, and MCP Practical Guide
A complete Spring AI guide for Java developers covering ChatModel, EmbeddingModel, ChatMemory, Tool Calling, MCP protocol, and RAG with Milvus. Build LLM apps in Spring Boot.
Read more →
·3 min
Spring AI 2.0 Deep Dive: A Java Developer's Guide to LLM Application Development
A deep dive into Spring AI 2.0: provider-agnostic APIs, RAG with vector databases, and how Java developers can build LLM apps using the Spring ecosystem.
Read more →
·4 min
The Complete Claude Code Guide: From Chat and CoWork to Automated Workflows
From Claude Chat to CoWork to Claude Code: a complete guide covering the three usage levels, Projects/Skills setup, MCP/CLI tool integration, and real automation workflows like fully automated knowledge video pipelines.
Read more →
·2 min
State Machine Voice Agents in Practice: Balancing Latency and Accuracy with Pipecat and Vapi
A deep dive into state machine-based voice AI agent architecture, comparing Pipecat Flows and Vapi Squad, and exploring the latency vs. accuracy trade-offs in agentic handoffs.
Read more →
·6 min
GPT-5.6 vs Grok 4.5 on the Same Day: A Packed Week of Flagship AI Model Launches
OpenAI's GPT-5.6 launches with Sawa, Terra, and Luna sub-models the same day as Musk's Grok 4.5, while Anthropic, Meta, and NVIDIA make their moves. A packed week of flagship AI launches.
Read more →
·3 min
Building a Real-Time AI Tutor for 5-Year-Olds: Technical Challenges and the Educational Balance
Exploring the core challenges of building real-time AI tutors for preschoolers: low-latency voice interaction, children's ASR, content safety guardrails, and AI as a guide rather than an answer machine.
Read more →
·4 min
9 AI Voice Recorders Compared: How to Choose Across the ¥198–¥899 Price Range
From ¥198 entry-level to ¥899 flagship, a full comparison of 9 mainstream AI voice recorders. Covering noise reduction, transcription accuracy, battery life, and discreetness to help you choose by scenario.
Read more →
·2 min
Deep Dive into GPT-Live-1: How OpenAI Taught Voice AI to Listen Instead of Interrupt
OpenAI's new voice model GPT-Live-1 focuses on fewer interruptions, recognizing pauses, and respecting conversational rhythm. A deep dive into its technical advances.
Read more →
·3 min
GPT Live Full-Duplex Voice Goes Live: Farewell to Walkie-Talkie Interaction, a Comprehensive Upgrade to AI Conversation
OpenAI officially launches GPT Live with a full-duplex architecture, enabling the AI to listen and speak at the same time, supporting interruptions, three reasoning tiers, and visual cards. A deep dive into its design and day-one issues.
Read more →
·4 min
Beware of AI Fake Marketing: Is the 'GPT-5.6 Release' a Scam?
A viral Bilibili video claiming the 'GPT-5.6 SOAR/TERRA/LURAL release' is full of fake model names, forged benchmarks, and risky third-party sites. We debunk it and show how to spot AI hype traps.
Read more →
·4 min
Hands-On Test of GPT Real-Time Voice: A Comprehensive Review of Dialect Recognition, Emotional Expression, and Role-Play
An in-depth hands-on test of GPT's real-time voice feature, covering Cantonese and Sichuanese dialect recognition, emotional tone switching, complex role-play, and cross-voice contextual memory—objectively presenting the true level and remaining gaps of AI voice interaction.
Read more →