Coqui XTTS Text-to-Speech

​

Overview

​

Installation

docker run --gpus=all -e COQUI_TOS_AGREED=1 --rm -p 8000:80 \
  ghcr.io/coqui-ai/xtts-streaming-server:latest-cuda121

​

Prerequisites

​

XTTS Server Setup

1. Docker Environment: Set up Docker with GPU support for optimal performance
2. XTTS Server: Run the XTTS streaming server container

​

Required Configuration

• Server URL: Configure the XTTS server endpoint (default: http://localhost:8000)
• Voice Selection: Choose one of the server’s studio speakers

​

Configuration

​

XTTSService

​

Settings

​

Usage

​

Basic Setup

import aiohttp
from pipecat.services.xtts.tts import XTTSService

async with aiohttp.ClientSession() as session:
    tts = XTTSService(
        settings=XTTSService.Settings(
            voice="Ana Florence",
        ),
        base_url="http://localhost:8000",
        aiohttp_session=session,
    )

​

With Language Configuration

import aiohttp
from pipecat.services.xtts.tts import XTTSService
from pipecat.transcriptions.language import Language

async with aiohttp.ClientSession() as session:
    tts = XTTSService(
        settings=XTTSService.Settings(
            voice="Ana Florence",
            language=Language.ES,
        ),
        base_url="http://localhost:8000",
        aiohttp_session=session,
    )

​

Notes

• Local server required: XTTS requires a locally running streaming server (via Docker). The service connects to this server over HTTP.
• Studio speakers: On startup, the service fetches available “studio speakers” from the server’s /studio_speakers endpoint. The voice setting must match one of these speakers; otherwise each request pushes an ErrorFrame.
• Audio resampling: XTTS natively outputs audio at 24kHz. The service automatically resamples to match the pipeline’s configured sample rate.
• GPU recommended: The XTTS server performs best with CUDA-enabled GPU acceleration. CPU inference is significantly slower.
• No API key required: XTTS runs locally, so no external API credentials are needed.