#speech
AudioLens — Audio inspection for VS Code
simzhou
Audio viewer for speech and ML workflows with waveforms, spectrograms, raw PCM, Kaldi wav ark, and Remote SSH support.
Markdown Read Aloud — Free Neural Text-to-Speech
RobinReiche
Read Markdown files aloud with free, high-quality neural voices — no API key, no sign-up. Text-to-speech (TTS) with automatic language detection across 75 languages, live 0.5×–2.5× speed, read from cursor/selection/heading, and sentence highlighting. Great for proofreading and listening to docs and
Markdown TTS: Read Aloud & AI Narration
AbhishekShr
Read markdown, code & docs aloud with text-to-speech, or let AI explain and narrate them. Neural + offline voices, git-diff narration, and voice input to Copilot Chat. Bring your own OpenAI, Anthropic, Groq, or free Gemini key.
Hey Claude
simonescigliuzzi
Voice access to Claude — just say "Hey Claude" to activate, like Siri or Alexa. Dictate tasks, ask questions, and send prompts to Claude Code hands-free.
Voice Agent
aditya-kangune
Voice input for AI coding assistants — speak your prompts instead of typing. Offline by default, optional OpenAI Whisper API for faster transcription.
Pronounce — Tech Word Pronunciation
sayit
Hover any tech word — hear how it's actually pronounced. 1880-entry sourced dictionary covering products, CLI tools, CS terms, AI/ML projects and researchers, and the cross-functional vocab (GTM, PLG, ARR, OKR, scrum, kanban …) tech folks use. Cross-platform: macOS `say`, Linux `espeak-ng`, Windows
Fish Audio MCP
acedatacloud
Fish Audio TTS — generate natural speech and browse the Fish voice library.
Speech Workbench
jayantjha
Play audio and overlay time-aligned STT/experiment data (transcripts, latency, confidence) for speech-recognition analysis.
Text to Speech Preview
DhakshinamoorthyA
Preview selected text or the active document with local system voices.
Maieutic
TenGallonTechnology
Lead-engineer codebase teaching, bounded AI-assisted coding, visual focus, and native VS Code voice conversation.