xtts-multilingual / README.md
Loomis Green
Update API: Add speakers directory, LFS tracking, and /speakers endpoint
c16f3f2
metadata
title: XTTS-v2 Multilingual
emoji: 🗣️
colorFrom: yellow
colorTo: red
sdk: docker
pinned: false
license: other

XTTS-v2 Multilingual TTS API

This Space hosts the Coqui XTTS-v2 model for high-quality multilingual text-to-speech with voice cloning.

API Usage

Generate Audio

Endpoint: POST /generate

Parameters:

  • text (string): The text to speak.
  • language (string): Language code (e.g., "en", "es", "de").
  • speaker_wav (file, optional): A WAV file (~6s) for voice cloning.
  • speaker_id (string, optional): Filename of a stored speaker (e.g., "default.wav").

Example (Stored Voice):

curl -X POST "https://YOUR_SPACE_URL/generate" \
  -F "text=Hello" \
  -F "language=en" \
  -F "speaker_id=default.wav" \
  --output out.wav

Supported Languages

English (en), Spanish (es), French (fr), German (de), Italian (it), Portuguese (pt), Polish (pl), Turkish (tr), Russian (ru), Dutch (nl), Czech (cs), Arabic (ar), Chinese (zh-cn), Japanese (ja), Hungarian (hu), Korean (ko).