README.md

metadata

title: Tts Api
emoji: 🚀
colorFrom: indigo
colorTo: yellow
sdk: docker
pinned: false

TTS API

A FastAPI-based Text-to-Speech API using XTTS-v2 for voice cloning.

Features

• Convert text to speech using voice cloning
• Upload reference speaker audio files
• Support for multiple languages
• RESTful API with automatic documentation
• Docker support

Setup

Local Development

1. Install dependencies:

pip install -r requirements.txt

2. Run the API:

python app.py

The API will be available at http://localhost:8000

Using Docker

1. Build the Docker image:

docker build -t tts-api .

2. Run the container:

docker run -p 8000:8000 tts-api

API Endpoints

Health Check

• GET /health - Check API status

Text-to-Speech

• POST /tts - Convert text to speech with uploaded speaker file
  • Parameters:
    • text (form): Text to convert to speech
    • language (form): Language code (default: "en")
    • speaker_file (file): Reference speaker audio file

API Documentation

• GET /docs - Interactive API documentation (Swagger UI)
• GET /redoc - Alternative API documentation

Usage Examples

Using Python requests

import requests

# Prepare the request
url = "http://localhost:8000/tts"
data = {
    "text": "Hello, this is a test of voice cloning!",
    "language": "en"
}
files = {
    "speaker_file": open("path/to/speaker.wav", "rb")
}

# Make the request
response = requests.post(url, data=data, files=files)

# Save the generated audio
if response.status_code == 200:
    with open("output.wav", "wb") as f:
        f.write(response.content)
    print("Speech generated successfully!")

Using curl

curl -X POST "http://localhost:8000/tts" \
  -F "text=Hello, this is a test!" \
  -F "language=en" \
  -F "speaker_file=@path/to/speaker.wav" \
  --output generated_speech.wav

Using the provided client example

python client_example.py

Requirements

• Python 3.8+
• CUDA-compatible GPU (recommended for faster processing)
• Audio file in supported format (WAV, MP3, etc.) for speaker reference

Model

This API uses the XTTS-v2_C3PO model for voice cloning, which is automatically downloaded when building the Docker image.