Tone Helper (backend)

Backend of speech synthesis application.
Explore the docs »

View Demo · Report Bug · Request Feature

Table of Contents

1. About
2. Getting Started
   • Prerequisites
   • Installation
3. API Discription
4. Contributing
5. Contact

About

The back-end server for speech synthesis applications, Tone Helper.

With the API provided by the server, you can do:

• speech recognition
• pitch detection
• file conversion
• speech synthesis

Of course, since your needs may be different, you are very welcome to suggest changes by forking this repo and creating a pull request or opening an issue!

Getting Started

Prerequisites

• Python 3.7
• HTTPS Server

Installation

1. Clone the repo

   git clone https://github.com/Shulammiteya/Tone-Helper-Backend.git

2. Install libraries

    pip3 install pydub SoundFile pyworld google-cloud-core

3. Create your own credential file in the root directory

   touch ./sample.json

4. Run the server

    python3 backend.py

API Discription

API	stt	tune	getURL
Method	POST	POST	GET

---

/stt

  input：

Key	Type	Value	Description
audio	audio/m4a		Audio files for speech recognition, pitch detection, and transcoding

  output：

Key	Type	Value	Description
audio	base64	...BwbGVhc3VyZS4=	WAV file encoded in base64
wordInfo	array	[    {          "word": "一",          "start": 27002,          "end": 98000,          "f0": 440.15,          "f0Start": 54,          "f0End": 196       },       {          ...       },       ...    ]	"word": the Speech-recognized text    "start": the starting position in the audio array    "end": the end position in the audio array    "f0": the average F0    "f0Start": the starting position in the f0 array    "f0End": the end position in the f0 array

---

/tune

  input：

Key	Type	Value	Description
audio	audio/wav		Audio file to be tuned
f0	JSON	{    659.26,       659.26,       440.00,       ...    }	Designated F0

  output：

Key	Type	Value	Description
data	base64	...BwbGVhc3VyZS4=	Synthesized audio encoded in base64

---

/getURL

  output：

Key	Type	Value	Description
data	string	https://youtu.be/...	Introductory video URL

Contributing

Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

Contact

About me: Hsin-Hsin, Chen - shulammite302332@gmail.com

Project Link: https://github.com/Shulammiteya/Tone-Helper-Backend