#speech-to-text coding
54 related articles
·3 min
Qwen-Audio-3.0-ASR-Flash Released: A New Speech Recognition Benchmark with 95% Medical Terminology Recall
Qwen releases Qwen-Audio-3.0-ASR-Flash speech recognition model with 95.36% medical and 93.24% industrial terminology recall. Features context consistency, domain-term recognition, custom hotwords, and speech polishing across streaming and file transcription versions.
Read more →
·3 min
LiveKit Agents: A Comprehensive Guide to the Open-Source Framework for Building Real-Time Voice AI Agents
Deep dive into the LiveKit Agents open-source framework for building real-time voice AI agents using STT, LLM, and TTS modules with production-ready deployment capabilities.
Read more →
·3 min
Bolcho AI: A Voice Agent Platform Built for India's Multilingual Market
Bolcho AI is a voice AI platform for India's market, supporting Hindi, Tamil and more local languages with ultra-low latency, telephony integration, and flexible BYO model architecture for enterprise AI agents.
Read more →
·3 min
Capptivo: A Detailed Review of the Free Open-Source Screen Recording & Presentation Editor
Capptivo is a free open-source screen recorder and presentation editor for macOS, Windows, and Linux with cursor-following zoom, local caption burn-in, and no account or subscription required.
Read more →
·2 min
ViiTor Translate: A Cross-Platform Real-Time Subtitle Translation Tool That Gets the Jokes
ViiTor Translate is a real-time subtitle translation tool focused on contextual understanding, supporting iOS, Android, and Chrome for Vtuber, K-pop, and anime fans with floating subtitle overlays.
Read more →
·3 min
Gstack Agents: Open-Source AI Expert Panel Joins Your Google Meet Video Calls
Gstack Agents is an MIT open-source tool that adds 18+ AI personas (CEO, CSO, YC partner, etc.) as voice bots to Google Meet, providing real-time multi-perspective structured feedback on your demos.
Read more →
·3 min
Gstack Agents: Open-Source AI Expert Panel Joins Your Google Meet Video Conferences
Gstack Agents is an MIT open-source tool that adds 18+ AI personas (CEO, CSO, YC Partner, etc.) as voice bots to Google Meet, providing real-time multi-perspective structured feedback on your product demos.
Read more →
·2 min
Tackly: An AI-Powered Note Tool That Draws Mind Maps in Real Time, Designed for People with ADHD
Tackly is an AI-powered note tool that maps voice and text to 20 thought node types in real time, auto-generating visual mind maps. Designed for ADHD users, it supports meetings, voice memos, and text structuring.
Read more →
·2 min
Tackly: An AI-Powered Note Tool That Draws Mind Maps in Real Time, Designed for People with ADHD
Tackly is an AI-powered note tool that maps voice and text to 20 thought node types in real time, auto-generating visual mind maps. Designed for ADHD users, it supports meetings, voice memos, and text structuring.
Read more →
·2 min
Wisprkey: A Free Tool That Enables Voice Input in Any Mac App
Wisprkey is a free Mac voice input tool with a global shortcut for voice-to-text in any app, claiming 98% accuracy and 31-language support.
Read more →
·2 min
Speech To Markdown: Local AI Voice-to-Structured Markdown Note-Taking Tool
Speech To Markdown is a free macOS/iOS app that converts voice to structured Markdown notes using local LLMs. Fully offline, no API keys needed, with global hotkey dictation.
Read more →
·3 min
GitHub Daily · July 27: AI Agent Skill Ecosystem Explodes, Claude's Capability Boundaries Keep Expanding
GitHub Trending July 27: AI Agent Skills explode as claude-video, impeccable, and last30days-skill extend model capabilities without modifying models themselves.
Read more →
·4 min
Zero-Code AI Voice Agents with Claude Code: 5 Real-World Business Scenarios Unpacked
Build a production AI voice agent with Claude Code + Telnyx single-stack — no code needed, live phone number in 5 minutes. Covers 5 business scenarios including appointment booking, lead qualification, and support triage.
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 →
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 →
·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 →
·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 →
·2 min
Why Does Speech-to-Text Keep Failing? A Practical Guide to Optimizing Messy Audio Transcription
Meeting recordings, mixed languages, and background noise causing speech-to-text to drop words or produce gibberish? This article dives deep into ASR hallucination causes and offers practical solutions.
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 →