Rapida
Rapida is an open-source voice AI orchestration platform for building real-time conversational voice agents, combining audio streaming, speech-to-text, text-to-speech, voice activity detection, multi-channel integration and observability.
Rapida is an open-source voice AI orchestration platform for real-time conversational voice agents. It provides both a managed platform and a framework, aimed at agencies and enterprises that want to self-host or run managed while keeping control of data, credentials, models, prompts, tools and integrations.
It streams and processes audio with low latency over gRPC, and includes retries, error handling, call lifecycle management and health checks for production use. It provides call logs, streaming events, tool traces, latency breakdowns, metrics and dashboards for observability, and lets operators build custom tools and lock down API surfaces for governance.
Rapida is written in Go and is deployed with Docker Compose; a full local setup needs Docker, the Just command runner, Go, Node.js and at least 16GB of RAM.