Murf AI

Text-to-speech service implementation using Murf AI’s streaming WebSocket API

Overview

MurfTTSService provides real-time text-to-speech synthesis using Murf AI’s WebSocket streaming API. It supports voice customization options including style, rate, pitch, variation, and custom pronunciation dictionaries.

Source Repository

Source code, examples, and issues for the Murf AI integration

PyPI Package

The pipecat-murf-tts package on PyPI

Murf API

Learn more about the Murf AI API and available voices

API Keys

Sign up and obtain your Murf API key from the dashboard

Installation

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

uv add pipecat-murf-tts

Prerequisites

Murf Account Setup

Before using the Murf TTS service, you need:

1. Murf Account: Sign up at Murf AI
2. API Key: Obtain your API key from the dashboard

Required Environment Variables

• MURF_API_KEY: Your Murf API key for authentication

Configuration

api_key · str · required

Murf API key for authentication.

url · str · default: "wss://global.api.murf.ai/v1/speech/stream-input"

WebSocket URL for the Murf TTS API.

params · MurfTTSService.InputParams · default: "None"

Voice customization parameters. See Input Parameters below.

text_aggregation_mode · TextAggregationMode · default: "None"

How to aggregate incoming text before synthesis.

Input Parameters

Voice settings passed via the params constructor argument using MurfTTSService.InputParams(...).

Parameter	Type	Default	Range/Options	Description
voice_id	str	"Matthew"	Any valid Murf voice ID	Voice identifier for TTS synthesis.
style	str	"Conversational"	Voice-specific styles	Voice style (e.g., "Conversational", "Narration").
rate	int	0	-50 to 50	Speech rate adjustment.
pitch	int	0	-50 to 50	Pitch adjustment.
pronunciation_dictionary	dict	None	Custom pronunciation mappings	Dictionary for custom word pronunciations.
variation	int	1	0 to 5	Variation in pause, pitch, and speed (Gen2 only).
multi_native_locale	str	None	Language codes (e.g., "en-US")	Language for Gen2 model audio.
model	str	"FALCON"	"FALCON", "GEN2"	The model to use for audio output.
sample_rate	int	44100	8000, 16000, 24000, 44100, 48000	Audio sample rate in Hz.
channel_type	str	"MONO"	"MONO", "STEREO"	Audio channel configuration.
format	str	"PCM"	"MP3", "WAV", "FLAC", "ALAW", "ULAW", "PCM", "OGG"	Audio output format.

Available parameters and defaults are defined by the integration. See the source repository for the authoritative, up-to-date list.

Usage

import os

from pipecat_murf_tts import MurfTTSService

tts = MurfTTSService(
    api_key=os.getenv("MURF_API_KEY"),
    params=MurfTTSService.InputParams(
        voice_id="Matthew",
        style="Conversational",
        rate=0,
        pitch=0,
        sample_rate=44100,
        format="PCM",
    ),
)

# ... add tts to your pipeline:
pipeline = Pipeline([
    context_aggregator.user(),
    llm,
    tts,
    context_aggregator.assistant(),
])

Compatibility

Tested with Pipecat v0.0.108. Check the source repository for the latest tested version and changelog.