rapidaai/voice-ai

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.

What it solves

Rapida is an open-source voice AI orchestration platform designed for agencies and enterprises. It eliminates vendor lock-in by allowing users to maintain ownership of their data, credentials, and deployment boundaries while providing the scale and reliability needed for production-grade real-time voice workloads.

How it works

Built in Go and utilizing the gRPC protocol for low-latency, bidirectional communication, Rapida acts as an orchestration layer. It allows developers to integrate their own choice of LLMs (such as OpenAI or Anthropic) and custom inference, as well as STT/TTS providers and telephony channels. The platform consists of multiple services including an API Gateway, Assistant API, Endpoint API, and Integration API, which can be deployed via Docker.

Who it’s for

It is primarily aimed at agencies building white-label client deployments and enterprises requiring private, scalable voice infrastructure and internal AI operations.

Highlights

  • Provider Agnostic: Support for bringing your own model and custom inference.
  • Real-time Performance: Low-latency audio streaming and processing via gRPC.
  • Production-Ready: Includes built-in retries, error handling, call lifecycle management, and full observability (logs, metrics, and dashboards).
  • Deployment Flexibility: Supports both managed and self-hosted options with a focus on data ownership.
  • Enterprise Governance: Tools for managing multi-client delivery and audit-friendly controls.

Related

  • Project
    openocta/openocta

    A desktop AIOps agent for Windows and macOS that automates IT operations tasks like alert analysis and system inspection through natural language and toolchain integration.

  • Dispatch
    Paca: An Open-Source, AI-Native Alternative to Jira

    Paca is a self-hosted, open-source project management platform designed for Scrum teams where AI agents and humans collaborate as equal teammates on a shared Scrumban board.

  • Project
    akdeb/ElatoAI

    A framework for deploying real-time voice AI models on ESP32 devices, enabling low-latency speech-to-speech conversations via edge functions.

  • Project
    landingbj/LinkMind

    An enterprise-grade multimodal AI middleware that provides a unified API layer for managing multiple model providers, RAG, and agent runtimes with centralized routing and governance.

  • Project
    omnara-ai/omnara

    An open source platform for running managed agents that handles execution and state, allowing developers to to choose their own models, tools, and machines.