R_REDDYX.XYZ
AITypeScript★ 400⑂ 88 forksApache-2.0

katipally/openlive

OPEN VOICE+VISION FOR AI

OpenLive — open on‑device voice+vision layer for AI agents. Supports any model or coding agent; the full speech loop (VAD, STT, TTS, barge‑in) runs locally — an open alternative to ElevenLabs, Gemini Live and OpenAI Realtime.

// KEY FEATURES

  • Performs VAD, STT and TTS entirely on device, ensuring low latency.
  • Supports barge‑in: user speech interruption without losing frames.
  • Works with any LLM or coding agent: Claude Code, Codex, Cursor via TypeScript API.
  • Includes on‑device vision layer for processing images in real time with the voice stream.
#claude-code#cli#codex#coding-agents#conversational-ai#cursor#hermes#local-first#open-source#openai-realtime#opencode#openlive
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

ImageIndexer: Auto-tagging photos via LLM★ 400GPTPortal: LLM Chat Web App★ 400WP-AUTOPLUGIN: PLUGINS WITHOUT EXTRA★ 400WIRESHARK‑MCP: AI PACKET ANALYSIS★ 400Claude Plugin for Elixir★ 401DUCTOR: CONTROL AI FROM TELEGRAM★ 401

← FULL CATALOG

katipally/openlive — Open Voice+vision For AI | REDDYX AI