API Documentation

Complete reference for integrating Hoppou AI TTS into your applications. OpenAI-compatible endpoints powered by Pocket TTS.

Overview

The Hoppou TTS API provides OpenAI-compatible text-to-speech endpoints powered by Pocket TTS. Generate natural-sounding speech from text with built-in or custom cloned voices.

Base URL

url

https://tts-api.barricade.dev

Quick Start

Get started in seconds. The API is fully compatible with OpenAI's TTS client libraries.

from openai import OpenAI

client = OpenAI(
    api_key="h_ai_your_key_here",
    base_url="https://tts-api.barricade.dev/v1"
)

response = client.audio.speech.create(
    model="tts-1",
    voice="alba",
    input="Hello, world! This is the Hoppou TTS API."
)

response.stream_to_file("output.mp3")

Features

🎯OpenAI Compatible

Drop-in replacement for /v1/audio/speech

⚡Low Latency

~200ms to first audio chunk

🎭Voice Cloning

Clone voices from 3-30 second audio samples

🔊Multiple Formats

PCM, WAV, MP3, and Opus output

📡Streaming

HTTP chunked & WebSocket streaming

🛡️Production Ready

Rate limiting, Fail2Ban, CORS