Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

starlog/MeloTTS-Docker-API-Server

Folders and files

NameName
Last commit message
Last commit date

Latest commit

History

28 Commits

Repository files navigation

MeloTTS Docker API Server

A quick easy way to access MeloTTS through REST API calls.

Build Image

Assuming you have docker installed and setup.

(This might take a bit because MeloTTS is a big dependency)

Local

git clone git@github.com:timhagel/MeloTTS-Docker-API-Server.git
cd MeloTTS-Docker-API-Server
docker build -t timhagel/melotts-api-server .

Docker Hub

docker pull timhagel/melotts-api-server

Languages and Speakers

Language

  • EN - English
  • ES - Spanish
  • FR - French
  • ZH - Chinese
  • JP - Japanese
  • KR - Korean

Speaker IDs

  • EN-US - American English accent
  • EN-BR - British English accent
  • EN_INDIA - Indian English accent
  • EN-AU - Australian English accent
  • EN-Default - Default English accent
  • Notice! Currently only English accents are working, and other accents are returning an error. This does not mean that other languages do not work!

Running

Run (CPU) (English)

docker run --name melotts-server -p 8888:8080 -e DEFAULT_SPEED=1 -e DEFAULT_LANGUAGE=EN -e DEFAULT_SPEAKER_ID=EN-Default timhagel/melotts-api-server

Run (GPU) (English)

docker run --name melotts-server -p 8888:8080 --gpus=all -e DEFAULT_SPEED=1 -e DEFAULT_LANGUAGE=EN -e DEFAULT_SPEAKER_ID=EN-Default timhagel/melotts-api-server

Call API

localhost:8888/convert/tts

Use Environment Defaults

Response: .wav

Post body:
{
 "text": "Put input here"
}
Example curl command:
curl http://localhost:8888/convert/tts \
--header "Content-Type: application/json" \
-d '{ "text": "Put input here" }' \
--output "example.wav"

Customize (Everything except for "text" is optional)

Response: .wav

Post body:
{
 "text": "input",
 "speed": "speed",
 "language": "language",
 "speaker_id": "speaker_id"
}
Example curl command:
curl http://localhost:8888/convert/tts \
--header "Content-Type: application/json" \
-d '{
 "text": "Put input here",
 "speed": "0.5",
 "language": "EN",
 "speaker_id": "EN-BR"
}' \
--output "example.wav"

Acknowledgement

This is just an API server for the awesome work of MeloTTS from MyShell

About

A docker image to access MeloTTS through API calls

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

Contributors

Languages

  • Python 84.7%
  • Dockerfile 15.3%

AltStyle によって変換されたページ (->オリジナル) /