VoxServe Documentation

VoxServe is a streaming-centric serving system for Speech Language Models (SpeechLMs), supporting both text-to-speech (TTS) and speech-to-speech (STS) workloads.

Getting Started

• Quickstart
  • Prerequisites
  • Install
  • Run the server
  • Send a request
  • Notes
• Core Concepts
  • Overview
  • Motivation
  • Innovation

Reference

• API Reference
  • Base URL
  • POST /generate
  • GET /health
• Python API
  • Package overview
  • Key modules
• CLI Reference
  • Usage
  • Arguments
• Supported Models
  • Text-to-speech (TTS)
  • Speech-to-speech (STS)
  • Notes
• Architecture
  • High-level components
  • Repository map
  • Execution flow (simplified)

Contributing

• Development