API Documentation
Overview
The Hoppou AI API provides OpenAI-compatible text-to-speech and speech-to-text endpoints. Generate natural-sounding speech from text with built-in or custom cloned voices, and transcribe audio files with Whisper-powered STT.
Powered by Pocket TTS and faster-whisper. Drop-in compatible with OpenAI SDKs.
Base URL
https://api.hoppou.ai/ttsQuick 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://api.hoppou.ai/tts/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 and /v1/audio/transcriptions. Use existing SDKs without changes.
Low Latency
~200ms to first audio chunk with HTTP streaming, even faster with WebSockets.
Voice Cloning
Clone any voice from a 3-30 second audio sample. Use custom voices via the API Portal.
Multiple Formats
Output in PCM, WAV, MP3, or Opus. Choose the right format for your use case.
Streaming
HTTP chunked transfer and WebSocket streaming for real-time playback.
Speech to Text
Whisper-powered transcription with 99+ language support and auto-detection.