Sign inSign up

twirapp/silero-tts-api-server

By twirapp

•Updated over 2 years ago

This is a simple server that uses Silero models to convert text to audio files over HTTP

Image
1

2.4K

twirapp/silero-tts-api-server repository overview

Banner

Github Repository⁠

⁠Languages supported

All models are from the repository: snakers4/silero-models⁠

LanguageModelSpeakers
Russianv4_ru5: aidar, baya, kseniya, xenia, eugene
Ukrainianv4_ua1: mykyta
Uzbekv4_uz1: dilnavoz
Englishv3_en118: en_0, en_1, ..., en_117
Spanishv3_es3: es_0, es_1, es_2
Frenchv3_fr6: fr_0, fr_1, fr_2, fr_3, fr_4, fr_5
Germanv3_de5: bernd_ungerer, eva_k, friedrich, hokuspokus, karlsson
Tatarv3_tt1: dilyara
Mongolianv3_xal2: erdni, delghir

⁠Launch a docker container

docker run --rm -p 8000:8000 twirapp/silero-tts-api-server

⁠Example of use via docker compose

version: '3'
services:
    silero-tts-api-server:
        image: twirapp/silero-tts-api-server
        ports:
            - "8000:8000"
        environment:
            - TEXT_LENGTH_LIMIT=930
            - MKL_NUM_THREADS=8

⁠Documentation

You can view the automatically generated documentation based on OpenAPI at:

ProviderUrl
Swagger⁠https://localhost:8000/schema/⁠
ReDoc⁠https://localhost:8000/schema/redoc⁠
Stoplight Elements⁠https://localhost:8000/schema/elements⁠
RepiDoc⁠https://localhost:8000/schema/repidoc⁠
OpenAPI schema yamlhttps://localhost:8000/schema/openapi.yaml⁠
OpenAPI schema jsonhttps://localhost:8000/schema/openapi.json⁠

⁠Endpoints

  • GET /generate - Generate audio in wav format from text. Parameters: text speaker sample_rate, pitch, rate
  • GET /speakers - Get list of speakers

sample_rate can be set from 8 000, 24 000, 48 000 pitch and rate can be set from 0 to 100

⁠Environment variables

  • TEXT_LENGTH_LIMIT - Maximum length of the text to be processed. Default is 930 characters.
  • MKL_NUM_THREADS - Number of threads to use for generating audio. Default number of threads: number of CPU cores.

⁠Considerations for the future

This repository is dedicated to twir.app and is designed to meet its requirements.

TwirApp needs to generate audio using the CPU. If support for other devices such as cuda or mps is needed, please open an issue⁠.

Tag summary

Content type

Image

Digest

sha256:99bad1a53…

Size

614.5 MB

Last updated

over 2 years ago

docker pull twirapp/silero-tts-api-server