Neuphonic

The NeuphonicTTSService provides ultra-low latency, high-fidelity text-to-speech using Neuphonic's WebSocket and HTTP APIs. It is designed for human-like conversational AI.

Installation

pip install "piopiy-ai[neuphonic]"

Prerequisites

• A Neuphonic API key (Get yours here).
• Set your API key in your environment:

  export NEUPHONIC_API_KEY="your_api_key_here"

Configuration

NeuphonicTTSService Parameters

Parameter	Type	Default	Description
api_key	str	Required	Your Neuphonic API key.
voice_id	str	None	ID of the voice to use.
sample_rate	int	22050	Audio sample rate (default 22050Hz).
params	InputParams	InputParams()	Synthesis settings.

InputParams

Parameter	Type	Default	Description
language	Language	Language.EN	Language for synthesis.
speed	float	1.0	Speech speed multiplier.

Usage

Basic Setup (Streaming)

import os
from piopiy.services.neuphonic.tts import NeuphonicTTSService

tts = NeuphonicTTSService(
    api_key=os.getenv("NEUPHONIC_API_KEY"),
    voice_id="your_voice_id"
)

Notes

• High Fidelity: Default sample rate is 22.05kHz, providing crisp and clear audio.
• Stop Control: Supports the <STOP> tag to gracefully finish/flush synthesis segments.
• SSE Support: An alternative NeuphonicHttpTTSService is available if you prefer Server-Sent Events over WebSockets.