Edge-TTS Service

A simple Text-to-Speech service using Microsoft Edge TTS.

Features

  • ๐ŸŒ Support 75+ languages
  • ๐ŸŽค Multiple voices per language
  • โš™๏ธ Adjustable speed, pitch, and volume
  • ๐Ÿ”Œ Easy API access via gradio_client

Usage

Web Interface

Just visit the Space URL and use the interface!

API Usage

from gradio_client import Client

client = Client("YOUR_USERNAME/YOUR_SPACE_NAME")

result = client.predict(
    text="Xin chร o, ฤ‘รขy lร  test TTS",
    voice="vi-VN-HoaiMyNeural | Female",
    rate=0,
    pitch=0,
    volume=0,
    api_name="/predict"
)

audio_file = result[0]
status = result[1]
print(f"Audio saved to: {audio_file}")

Supported Languages

Vietnamese, English, Portuguese, Spanish, French, German, Japanese, Korean, Chinese, and 60+ more!

License

MIT License

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support