Skip to content

TTS Provider Setup Guide (Runbook Index)

This page intentionally avoids duplicating provider setup details. It defines where each setup workflow lives so users can choose the right depth.

Scope: - Use Getting Started — STT and TTS for first successful end-to-end speech requests. - Use TTS Providers Getting Started for provider comparison and first successful synthesis. - Use the canonical runbook below for deep provider setup, tuning, and troubleshooting.

Canonical deep runbook: - Docs/STT-TTS/TTS-SETUP-GUIDE.md

Table of Contents

Commercial Providers

Use the commercial-provider section in the canonical runbook: - Commercial Providers

OpenAI

  • Setup and model notes: OpenAI

ElevenLabs

Local Model Providers

Use the local-provider section in the canonical runbook: - Local Model Providers

Model Auto-Download Controls

Qwen3-TTS Setup

LuxTTS Setup

Kokoro Setup

PocketTTS ONNX Setup

Higgs Audio V2 Setup

Chatterbox Setup

Dia Setup

  • Full setup and dialogue-specific notes: Dia Setup

VibeVoice Setup (Community Reference)

Voice Cloning Setup

Use the canonical voice-cloning section: - Voice Cloning Setup - Preparing Voice Reference Audio - Using Voice Cloning via API

Setup Verification

Run verification/smoke tests from: - Setup Verification - Quick Test for Each Provider

Performance Optimization

Performance guidance is maintained in: - Performance Optimization - GPU Acceleration - CPU Optimization

Troubleshooting

Troubleshooting details are maintained in: - Troubleshooting - Common Issues - Health Check

Resource Requirements Summary

See: - Resource Requirements Summary

Best Practices

See: - Best Practices