HUB
Sign inSign up

tmcx/tts-translator

By tmcx

•Updated over 2 years ago

Translation API and TTS. 318 voices and 33 languages. Using edge-tts and libretranslate.

Image
Languages & frameworks
API management
Machine learning & AI
0

2.6K

tmcx/tts-translator repository overview

⁠Description

TTS-Translator is a Docker image that contains an API for translating text and converting text to speech. It also provides the functionality to combine both actions to provide text-to-speech translation.

⁠Environment Variables

  • LT_LOAD_ONLY: Defines the languages to be installed.

    • Default: "en,es".
    • Available: sq(Albanian), de(German), ar(Arabic), az(Azerbaijani), bn(Bengali), bg(Bulgarian), ca(Catalan), zh(Chinese), zt(Chinese (traditional)), cs(Czech), da(Danish), nl(Dutch), en(English), eo(Esperanto), et(Estonian), fi(Finnish), fr(French), el(Greek), he(Hebrew), hi(Hindi), hu(Hungarian), id(Indonesian), ga(Irish), it(Italian), ja(Japanese), ko(Korean), lv(Latvian), lt(Lithuanian), ms(Malay), nb(Norwegian), fa(Persian), pl(Polish), pt(Portuguese), ro(Romanian), ru(Russian), sr(Serbian), sk(Slovak), sl(Slovenian), es(Spanish), sv(Swedish), tl(Tagalog), th(Thai), tr(Turkish), uk(Ukrainian), ur(Urdu), vi(Vietnamese).
    • All unselected languages ​​will not work in the API.
  • API_PORT: Defines the port of the API.

    • Default: "8080"

⁠Features

  • Text translation.
  • Text-to-speech conversion.
  • Text-to-speech translation.

⁠Endpoints

  • POST /tts: Translates and/or transforms to text-to-speech.
    • HTTP Body:
    {
        "text": "Hello world!",           // [Required] Text to use
        "voice": {                        // [Optional] Voice configuration
            "name" : "es-AR-TomasNeural", // TTS voice. To list it use /tts/voices endpoint.
            "volume": -50,                 // Voice volume
            "pitch": -10,                 // Voice pitch
            "rate": -10                   // Voice rate
        },
        "translate": {                    // [Optional] Translation configuration
            "from": "en",                 // Source language
            "to": "es"                    // Target language
        }
    }
    
  • GET /tts/voices: Retrieves the voices available for text-to-speech.
  • POST /translate: Translates text.
    • HTTP Body:
    {
        "text": "Hello world!",           // [Required] Text to use
        "from": "en",                     // [Required] Source language. To list it use /translate/languages endpoint.
        "to": "es"                        // [Required] Target language. To list it use /translate/languages endpoint.
    }
    
  • GET /translate/languages: Retrieves the languages available for translate.

⁠Usage

To run this Docker image, you can use the following command:

docker run -d -e LT_LOAD_ONLY="en,es" -e API_PORT="8080" -p 8080:8080 tmcx/tts-translator:latest

⁠Author

TMCX⁠

⁠Repository

The source code of this project is available on GitHub⁠.

⁠License

This project is licensed under the LGPL-3 License⁠ for commercial use without the obligation to share the source code.

Tag summary

Content type

Image

Digest

sha256:15250e226…

Size

453.7 MB

Last updated

over 2 years ago

docker pull tmcx/tts-translator