tts-service

What problem does it solve?

This Skill provides a shared text-to-speech service for a multi-tenant Hungarian voice assistant platform, enabling real-time speech synthesis across tenants from a single deployment.

Core Features & Use Cases

• HTTP Interfaces: health checks at /health and speech synthesis at /speak; supports JSON with base64 audio payload or binary WAV responses.
• Model & Runtime: loads PiperVoice from ONNX with a configurable voice path and JSON config, controlled via environment variables.
• Multi-tenant & determinism: designed for multi-tenant deployments with deterministic startup and per-tenant voice consistency.
• Use Case: a company’s chatbot responds in Hungarian with natural-sounding speech, delivered to customers through a browser or app.

Quick Start

Configure the Piper voice parameters via PIPER_VOICE and PIPER_VOICE_JSON, start the FastAPI server, then POST text to /speak to obtain spoken output.