Mirai Text-to-Speech

​

Overview

• MiraiRealtimeLLMService, for Mirai’s speech-to-speech Realtime API (OpenAI Realtime protocol). Speech recognition, turn detection, the model and the voice run together on Mirai’s side, and this one service replaces STT, LLM and TTS.
• apply_output_lead(), which stops audio breaking up on phone calls over Pipecat’s websocket transports when the bot’s server is busy. It works with any TTS service.

​

Installation

uv add pipecat-mirai

​

Prerequisites

​

Mirai Account Setup

1. Mirai Account: Sign up in the Mirai console
2. API Key: Create an API key (sk_live_...) in the console
3. Voice Selection: Choose ashu, neha, shruti or sameer

​

Required Environment Variables

• MIRAI_API_KEY: Your Mirai API key for authentication

​

Configuration

​

Usage

import os

from pipecat.pipeline.pipeline import Pipeline
from pipecat_mirai import MiraiTTSService

tts = MiraiTTSService(
    api_key=os.getenv("MIRAI_API_KEY"),
    settings=MiraiTTSService.Settings(voice="shruti"),
)

pipeline = Pipeline([
    transport.input(),
    stt,
    context_aggregator.user(),
    llm,
    tts,
    transport.output(),
    context_aggregator.assistant(),
])

​

Phone calls

from pipecat_mirai import apply_output_lead

transport = FastAPIWebsocketTransport(websocket, FastAPIWebsocketParams(serializer=serializer, ...))
apply_output_lead(transport)  # up to 0.4 s ahead of real time

​

Compatibility