Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state management, and observability.
$ git clone https://github.com/rapidaai/voice-ai.gitOpen-source realtime voice agent server in Go with WebRTC (WHIP), barge-in, streaming STT/LLM/TTS pipelines, plugin system, multi-language SDKs, SIP telephony, ESP32 support & fully local mode.
SEPIA server to support open-source speech recognition via WebSocket connection.
Open-source voice agent OS. Rust runtime, AI-driven builder, sub second latency. Self-host everything.
Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.
Record your screen, ship a demo. Free and open-source, GPU-accelerated, no watermarks, no subscriptions. Windows, macOS, Linux. Actively maintained.
Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support.
Data from GitHub · snapshot Nov 13, 2026