# Voxray

## Docs

- [Extensions](https://voxray-cac3ed72.mintlify.app/build/extensions.md): Drop-in pipeline extensions for IVR navigation and voicemail detection in outbound Voxray agents.
- [Anthropic](https://voxray-cac3ed72.mintlify.app/build/integrations/anthropic.md): Claude LLM provider for Voxray. Supports the full Claude 3 and Claude 4 model families as the LLM stage of the STT → LLM → TTS pipeline.
- [AWS](https://voxray-cac3ed72.mintlify.app/build/integrations/aws.md): Use Amazon Transcribe (STT), Amazon Bedrock (LLM), and Amazon Polly (TTS) with Voxray. All three services are covered by the standard AWS SDK v2 credential chain — no separate API key is required.
- [ElevenLabs](https://voxray-cac3ed72.mintlify.app/build/integrations/elevenlabs.md): Use ElevenLabs for industry-leading TTS voice quality and Scribe-powered STT in your Voxray voice agent pipeline.
- [Groq](https://voxray-cac3ed72.mintlify.app/build/integrations/groq.md): Ultra-low-latency STT, LLM, and TTS provider powered by Groq's custom LPU hardware. A strong default choice when minimizing pipeline latency is the primary objective.
- [Ollama](https://voxray-cac3ed72.mintlify.app/build/integrations/ollama.md): Run open-source LLMs locally with Ollama as the LLM provider in your Voxray voice agent pipeline. No API key required.
- [OpenAI](https://voxray-cac3ed72.mintlify.app/build/integrations/openai.md): Full-stack voice provider for Voxray: STT, LLM, TTS, and Realtime. The default provider when no explicit provider is set.
- [Integrations Overview](https://voxray-cac3ed72.mintlify.app/build/integrations/overview.md): Voxray supports 30+ STT, LLM, TTS, and realtime providers. Mix and match across pipeline stages — use a different provider for each of STT, LLM, and TTS, or point all three at a single service.
- [Sarvam](https://voxray-cac3ed72.mintlify.app/build/integrations/sarvam.md): Sarvam STT and TTS integration for Indian language voice agents
- [MCP Tools](https://voxray-cac3ed72.mintlify.app/build/mcp-tools.md): Connect Voxray voice agents to external tools and services via the Model Context Protocol (MCP).
- [Plugin System](https://voxray-cac3ed72.mintlify.app/build/plugin-system.md): How Voxray's processor registry works, every built-in plugin, how to wire plugins in config, and a complete guide to writing and registering a custom processor in Go.
- [Full Cloud Voice Agent with OpenAI](https://voxray-cac3ed72.mintlify.app/build/tutorials/cloud-llm-openai.md): Run a complete voice pipeline using OpenAI Whisper for transcription, GPT-4o for reasoning, and OpenAI TTS for speech — all from a single API key.
- [Echo Bot](https://voxray-cac3ed72.mintlify.app/build/tutorials/echo-bot.md): Test your Voxray setup with zero API keys required. The echo processor reflects every text frame back as speech, letting you verify your transport, pipeline, and audio encoding end-to-end before wiring in real providers.
- [Local LLM with Ollama](https://voxray-cac3ed72.mintlify.app/build/tutorials/local-llm-ollama.md): Run a voice agent entirely on your own hardware — no cloud APIs, no data leaves your machine. Ollama handles LLM inference locally; Groq or OpenAI handle STT and TTS.
- [Tutorials Overview](https://voxray-cac3ed72.mintlify.app/build/tutorials/overview.md): Hands-on tutorials that take you from a zero-dependency echo bot to a production-grade multi-provider voice pipeline with telephony.
- [Production Voice Agent Pipeline](https://voxray-cac3ed72.mintlify.app/build/tutorials/production-pipeline.md): Build a production-grade voice agent using Groq STT, Anthropic Claude, and ElevenLabs TTS — with interruptions, VAD tuning, session recording, and transcript persistence.
- [Phone Calls with Twilio](https://voxray-cac3ed72.mintlify.app/build/tutorials/telephony-twilio.md): Connect a real phone number to your Voxray agent. Callers dial in over PSTN, Twilio bridges the call to your server via WebSocket, and your agent answers in real time.
- [Adding Providers](https://voxray-cac3ed72.mintlify.app/contributing/adding-providers.md): Step-by-step guide to adding a new STT, LLM, or TTS provider to Voxray
- [Contributing Guide](https://voxray-cac3ed72.mintlify.app/contributing/guide.md): How to contribute to Voxray: dev setup, code style, commits, and PR process
- [Testing](https://voxray-cac3ed72.mintlify.app/contributing/testing.md): Test structure, how to run tests, and testing conventions for Voxray contributors
- [Architecture](https://voxray-cac3ed72.mintlify.app/core-concepts/architecture.md): How Voxray is structured: layers, data flow, session lifecycle, frame types, and key packages.
- [Audio & VAD](https://voxray-cac3ed72.mintlify.app/core-concepts/audio-vad.md): Audio format standards, codec conversion, resampling, voice activity detection, and turn detection in Voxray.
- [Configuration](https://voxray-cac3ed72.mintlify.app/core-concepts/configuration.md): Complete reference for Voxray's JSON configuration file and environment variable overrides, following 12-factor app principles.
- [Pipeline & Processors](https://voxray-cac3ed72.mintlify.app/core-concepts/pipeline-processors.md): How the linear processor chain works, the Processor interface, built-in voice processors, and how to write a custom processor.
- [Providers & Services](https://voxray-cac3ed72.mintlify.app/core-concepts/providers-services.md): How Voxray abstracts STT, LLM, and TTS behind Go interfaces, and how to select any supported provider by changing a single config value.
- [Transport Layer](https://voxray-cac3ed72.mintlify.app/core-concepts/transport-layer.md): How Voxray connects to clients — WebSocket, WebRTC, telephony, and in-process transports, plus wire format options and session lifecycle.
- [Docker](https://voxray-cac3ed72.mintlify.app/deploy/docker.md): Build and run Voxray as a Docker container — single binary, minimal Alpine runtime, two build variants.
- [Docker Compose](https://voxray-cac3ed72.mintlify.app/deploy/docker-compose.md): Run Voxray locally or on a single host with Docker Compose — optional Redis for session persistence and horizontal scaling.
- [Observability](https://voxray-cac3ed72.mintlify.app/deploy/observability.md): Health endpoints, Prometheus metrics, structured logging, and alerting for Voxray in production.
- [Production Deployment](https://voxray-cac3ed72.mintlify.app/deploy/production.md): Checklist, TLS configuration, logging, resource limits, and graceful shutdown for running Voxray in production.
- [Scaling](https://voxray-cac3ed72.mintlify.app/deploy/scaling.md): Run Voxray from a single instance to a horizontally-scaled cluster: session store configuration, load balancer requirements, performance tuning, and storage at scale.
- [Security](https://voxray-cac3ed72.mintlify.app/deploy/security.md): API key authentication, CORS, request body limits, secrets management, and container hardening for Voxray.
- [Telephony](https://voxray-cac3ed72.mintlify.app/deploy/telephony.md): Connect Voxray to phone networks via Twilio, Telnyx, Plivo, Exotel, Daily.co, or LiveKit. Handle inbound calls with a real-time AI voice pipeline over provider WebSocket backhaul.
- [Your First Voice Agent](https://voxray-cac3ed72.mintlify.app/get-started/first-voice-agent.md): Build a working voice agent that greets users and answers questions — from a blank config to a live conversation in under 10 minutes.
- [Installation](https://voxray-cac3ed72.mintlify.app/get-started/installation.md): Install Voxray, set up your Go environment, and choose the right build for your transport needs.
- [Introduction](https://voxray-cac3ed72.mintlify.app/get-started/introduction.md): Config-driven Go server for real-time AI voice agents
- [WebRTC Quickstart](https://voxray-cac3ed72.mintlify.app/get-started/quickstart-webrtc.md): Build Voxray with Opus audio support and connect a browser client via WebRTC for real-time bidirectional voice.
- [Quickstart: WebSocket](https://voxray-cac3ed72.mintlify.app/get-started/quickstart-websocket.md): Run a real-time AI voice agent over WebSocket in under 5 minutes — no CGO or C compiler required.
- [API Reference](https://voxray-cac3ed72.mintlify.app/reference/api-reference.md): Complete HTTP and WebSocket API reference for the Voxray voice pipeline server.
- [Configuration Reference](https://voxray-cac3ed72.mintlify.app/reference/configuration-reference.md): Complete reference for all Voxray configuration fields and environment variable overrides
- [FAQ](https://voxray-cac3ed72.mintlify.app/reference/faq.md): Frequently asked questions about Voxray
- [Glossary](https://voxray-cac3ed72.mintlify.app/reference/glossary.md): Definitions of key terms used throughout the Voxray documentation
- [Provider Matrix](https://voxray-cac3ed72.mintlify.app/reference/provider-matrix.md): Complete matrix of all supported providers and their capabilities

## OpenAPI Specs

- [swagger](https://voxray-cac3ed72.mintlify.app/swagger.json)
- [openapi](https://voxray-cac3ed72.mintlify.app/api-reference/openapi.json)

## Optional

- [GitHub](https://github.com/Voxray-AI/Voxray)
- [Discord](https://discord.gg/voxray)