VozIA
STT TTS LLM
Sign In Open Dashboard

Voice AI Gateway

Enterprise-grade STT, TTS, LLM & Voice-to-Voice pipeline. One API. One gateway. All voice AI.

Self-hosted · OpenAI-compatible · Docker-ready · Multi-provider LLM

Four Pillars of Voice AI

Everything you need to build voice-powered applications, exposed as simple HTTP endpoints.

Voice-to-Voice

Full pipeline: Audio in → STT → LLM → TTS → Audio out. One API call, complete voice conversation.

Multi-Provider LLM

Ollama, OpenAI, or any compatible provider. Hot-swap without code changes. One endpoint, any model.

Real-Time Dashboard

Live metrics, health monitoring, animated charts. Enterprise-grade visibility into every request.

API Gateway

Auth, rate limiting, per-key quotas, structured logging. Production-ready from day one.

Architecture

A single gateway routes requests to specialized AI services running in Docker containers.

Any App / Service / Browser
HTTP / SSE
VozIA Gateway
Node.js + Express
Port 3100 · Auth · Rate Limiting · Metrics
POST /v1/stt
POST /v1/tts
POST /v1/chat
POST /v1/converse
Faster-Whisper
STT Service
Port 8100 · Docker
Kokoro Web
TTS Service
Port 8200 · Docker
Ollama / OpenAI
LLM Service
Port 11434 · Docker

Try It Live

Real responses from the running gateway. No mocks.

vozia-gateway
$

API Endpoints

OpenAI-compatible. Drop-in replacement for your existing voice stack.

MethodEndpointDescription
POST /v1/stt Speech-to-Text. Transcribe audio files.
POST /v1/tts Text-to-Speech. Synthesize audio from text.
POST /v1/chat LLM Chat with SSE streaming support.
POST /v1/converse Full voice pipeline: Audio → STT → LLM → TTS → Audio
GET /v1/voices List available TTS voices.
GET /v1/models List available LLM models.
GET /health Health check for all backend services.

Quick Start

# Voice-to-Voice in one curl command
curl -X POST http://localhost:3100/v1/converse \
  -H "Authorization: Bearer sk-your-key" \
  -F "audio=@question.wav" \
  -F 'bot_config={"system_prompt":"You are a helpful assistant","voice":"af_heart"}' \
  --output response.wav