Start recording when the user speaks
Repository Index
47,133 repositories indexed
121–144 of 172 · Most stars
:sweat_drops::metal: A mimetic poly-alloy of the Quicksilver scoring algorithm, essentially LiquidMetal. </Schwarzenegger Voice>
- fuzzy-matching
- fuzzy-search
- javascript
Let your AI agents call your phone over VoIP, and call them back. Your phone rings like a real call, even locked; a voice AI talks it through and returns the transcript. Self-hosted, open source, no phone numbers or Twilio.
- ai-agents
- android
- claude-code
- gemini-live
🗣 An overlay that gets your user’s voice permission and input as text in a customizable UI
- voice
- overlay
- input
- speech-to-text
A multi-model Muse: personal AI voice assistant on ESP32 - wake word or knob, any OpenAI-compatible brain (STT/chat/TTS mix-and-match), streaming replies, out of the box. Built on muse-gadget-sdk.
TranslatedZongzhu (宗主, "sect leader"): a Grok Bot voice terminal on the Waveshare 1.75C round-screen ESP32, with blinking eye expressions, subtitles and spoken readout, including firmware and backend source code (2.5.2.9)
- amoled
- desktop-robot
- esp32
- esp32-s3
A free skill for Claude Code and OpenCode (runs on a free model): one topic line in, a finished 15-25 s What If animated episode out. Every frame drawn in code (SVG + Remotion); voice and sound from ElevenLabs.
A command line tool that transforms Lua code
- code-generation
- lua
- luau
Gameserver, Voiceserver Webinterface
- game-server
- php
- voice-server
- webinterface
A Chrome browser extension that embeds ChatGPT as a hands-free voice assistant
Speech, voices, stories, audiobooks, dubbing and transcription, made on your Mac. Free and open source.
- speaker-diarization
- speech-synthesis
- speech-to-text
- text-to-speech
Make any NPC in any game talk back with Fish Audio: skills, a self-hosted voice server and tools for AI coding agents, with a full GTA V example.
- agent-skills
- claude-code
- fish-audio
- game-modding
Groki Bot desktop robot (M5Stack CoreS3): firmware, a voice and MCP gateway for your computer, and a hand-off to Grok Bot agents
Free offline AI voice studio for Windows — text-to-speech with cloned and built-in voices, and speech recognition with speakers. Russian done right. 100% local, one native .exe, zero Python.
- asr
- local-ai
- offline
- portable
A notch-style island for GNOME that keeps your day one glance away: music with synced lyrics, notifications, calendar, focus timer, tasks, screen time, a clipboard shelf and an AI assistant that installs and fixes things. In black or glass, and light on your system
- clipboard-manager
- gnome
- gnome-shell-extension
- linux
A Discord client without the web browser. Native, written in Rust, about 30 MB of RAM idle.
- chat
- desktop-app
- discord
- discord-client
The open-source video studio for AI agents. Plan, generate, and edit films on a local-first canvas with your own models and short drama video.
- ai
- ai-drama
- ai-drama-generator
- ai-video
AI motion graphics for YouTube explainer videos: 74 animated HTML explainer boards (charts, diagrams, Venn, timeline, heatmap) synced to your voice with Whisper, exported frame by frame with Chrome + FFmpeg. Every prompt + Claude skills. By TEIN AI.
AstrBot plugin and local HTTP service for Feiyu TTS, RVC v1 and optional score singing
Free, open-source, local alternative to ElevenLabs and Suno. AI sound effects, music with lyrics, text-to-speech and voice cloning on your own GPU (Stable Audio, ACE-Step and more). No account, no credits, offline. Windows/macOS app, HTTP API and a 21-tool MCP server for Claude Code and Cursor.
- local-ai
- mcp
- music-generation
- sound-effects
Live WhatsApp voice calls with Hermes: call your bot, or let Hermes call you. Hermes plugin + whatsapp-rust sidecar + Gemini Live.
- gemini-live
- hermes-agent
- hermes-plugin
- voice-assistant
A curated collection of papers and resources on voice agents, from spoken interaction to autonomous task execution.
TranslatedNo need to appear on camera: turn your ideas into videos with a script or a voice recording. Script- or voice-driven motion graphics with Codex and Remotion: real footage, captions, editable projects and 96 motion studies.
- agent-skills
- captions
- codex
- motion-graphics
Capacitor plugin for voice recording