Quickdial

Text-to-speech service implementation using Quickdial’s real-time TTS API

Overview

QuickdialTTSService generates speech from text using Quickdial’s real-time text-to-speech API. It extends Pipecat’s TTSService and pushes TTSAudioRawFrame audio into the pipeline. Quickdial streams audio as it’s generated and is priced per character.

Source Repository

Source code, examples, and issues for the Quickdial integration

PyPI Package

The pipecat-quickdial package on PyPI

Quickdial

Learn more about Quickdial and get an API key

Docs

Quickdial API reference (REST + WebSocket)

Installation

This is a community-maintained package distributed separately from pipecat-ai:

uv add pipecat-quickdial

Prerequisites

1. Quickdial account — sign up at web.quickdial.ai (100,000 characters free, no card required).
2. API key — create one in the dashboard.

Required environment variables

QUICKDIAL_API_KEY=qtts_live_your_key

Configuration

Parameter	Type	Default	Description
api_key	str	QUICKDIAL_API_KEY env var	Your Quickdial API key.
voice	str	"alba"	Voice name (see the voice catalog / GET /v1/voices).
base_url	str	https://api.quickdial.ai	API base URL.
sample_rate	int	24000	Output sample rate (Hz).
params	dict	None	Optional model knobs (e.g. temperature, speed).

Usage

import os

from pipecat_quickdial import QuickdialTTSService

tts = QuickdialTTSService(
    api_key=os.getenv("QUICKDIAL_API_KEY"),
    voice="alba",
)

# ...add `tts` to your Pipecat Pipeline([...])

Additional resources

• pipecat-quickdial on GitHub — source, example, and issues
• Quickdial API docs