Deprecated

PlayHT is shutting down their API on December 31st, 2025. PlayHTTTSService is deprecated and will be removed in a future version.

PlayHT

The PlayHTTTSService provides real-time text-to-speech synthesis using PlayHT's WebSocket API. It supports high-quality voice clones and a variety of pre-trained models.

Installation

pip install "piopiy-ai[playht]"

Prerequisites

• A PlayHT account, API key, and User ID (Get yours here).
• Set your credentials in your environment:

  export PLAYHT_API_KEY="your_api_key"
  export PLAYHT_USER_ID="your_user_id"

Configuration

PlayHTTTSService Parameters

Parameter	Type	Default	Description
api_key	str	Required	Your PlayHT API key.
user_id	str	Required	Your PlayHT user ID.
voice_url	str	Required	URL of the voice to use.
voice_engine	str	"Play3.0-mini"	Voice engine to use.
params	InputParams	InputParams()	Synthesis settings.

InputParams

Parameter	Type	Default	Description
language	Language	Language.EN	Language for synthesis.
speed	float	1.0	Speech speed multiplier.
seed	int	None	Random seed for consistency.

Usage

Basic Setup

import os
from piopiy.services.playht.tts import PlayHTTTSService

tts = PlayHTTTSService(
    api_key=os.getenv("PLAYHT_API_KEY"),
    user_id=os.getenv("PLAYHT_USER_ID"),
    voice_url="s3://voice-cloning-zero-shot/..."
)

Notes

• WebSocket Connection: This service maintains a persistent connection for low-latency streaming.
• HTTP Alternative: For non-streaming use cases, you can use PlayHTHttpTTSService.