Parler-TTS-Server

This repository provides a server with an OpenAI compatible API interface for Parler-TTS.

Table of Contents

• Quick Start
  • Prerequisites
  • Docker
  • Docker Compose
• Usage
  • Examples
    • Kannada
    • Hindi
  • Saving to File
  • Specifying a Different Format
  • Playing Back the Audio
  • Describing the Voice
  • OpenAI SDK Usage Example
• Citations
• License

Quick Start

Prerequisites

• Docker
• cURL

Docker

Run the server with the default model:

docker run --detach --volume ~/.cache/huggingface:/root/.cache/huggingface --publish 8000:8000 slabstech/parler-tts-server

Run the server with a fine-tuned model:

docker run --detach --volume ~/.cache/huggingface:/root/.cache/huggingface --publish 8000:8000 --env MODEL="ai4bharat/indic-parler-tts" slabstech/parler-tts-server

Docker Compose

Download the compose.yaml file and start the server:

curl -sO https://raw.githubusercontent.com/sachinsshetty/parler-tts-server/refs/heads/master/compose.yaml
docker compose up --detach parler-tts-server

Usage

Examples

Kannada

curl -s -H "content-type: application/json" localhost:8000/v1/audio/speech -d '{"input": "ಉದ್ಯಾನದಲ್ಲಿ ಮಕ್ಕಳ ಆಟವಾಡುತ್ತಿದ್ದಾರೆ ಮತ್ತು ಪಕ್ಷಿಗಳು ಚಿಲಿಪಿಲಿ ಮಾಡುತ್ತಿವೆ."}' -o audio_kannada.mp3

Output

• audio_kannada.mp3: Download

Hindi

curl -s -H "content-type: application/json" localhost:8000/v1/audio/speech -d '{"input": "अरे, तुम आज कैसे हो?"}' -o audio_hindi.mp3

Saving to File

curl -s -H "content-type: application/json" localhost:8000/v1/audio/speech -d '{"input": "Hey, how are you?"}' -o audio.mp3

Specifying a Different Format

curl -s -H "content-type: application/json" localhost:8000/v1/audio/speech -d '{"input": "Hey, how are you?", "response_type": "wav"}' -o audio.wav

Playing Back the Audio

curl -s -H "content-type: application/json" localhost:8000/v1/audio/speech -d '{"input": "Hey, how are you?"}' | ffplay -hide_banner -autoexit -nodisp -loglevel quiet -

Describing the Voice

curl -s -H "content-type: application/json" localhost:8000/v1/audio/speech -d '{"input": "Hey, how are you?", "voice": "Feminine, speedy, and cheerful"}' | ffplay -hide_banner -autoexit -nodisp -loglevel quiet -

OpenAI SDK Usage Example

An example of using the OpenAI SDK can be found here.

Citations

@misc{lacombe-etal-2024-parler-tts,
  author = {Yoach Lacombe and Vaibhav Srivastav and Sanchit Gandhi},
  title = {Parler-TTS},
  year = {2024},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/huggingface/parler-tts}}
}

@misc{lyth2024natural,
  title = {Natural language guidance of high-fidelity text-to-speech with synthetic annotations},
  author = {Dan Lyth and Simon King},
  year = {2024},
  eprint = {2402.01912},
  archivePrefix = {arXiv},
  primaryClass = {cs.SD}
}

License

This project is licensed under the MIT License. See the LICENSE file for details.