Utility for Google Text-To-Speech batch audio files generator. Ideal for prompt files creation with Google voices for application in offline IVRs

Last update: Aug 19, 2021

Overview

Google Text-To-Speech Batch Prompt File Maker

Are you in the need of IVR prompts, but you have no voice actors? Let Google talk your prompts like a pro! This repository contains a tool for generating Google Text-To-Speech audio files in batch. It is ideal for offline prompts creation with Google voices for application in IVRs

In order to use this repository, clone the contents in your local environment with the following console command:

git clone https://github.com/ponchotitlan/google_text-to-speech_prompt_maker.git

Once cloned, follow the next steps for environment setup:

1) GCP account setup

Before adjusting up the contents of this project, it is neccesary to setup the Cloud Text-to-Speech API in your Google Cloud project:

Follow the official documentation for activating this API and creating a Service Account
Generate a JSON key associated to this Service Account
Save this JSON key file in the same location as the contents of this repository

2) CSV and YAML files

Prepare a CSV document with the texts that you want to convert into prompt audio files. The CSV must have the following structure:

    <FILE NAME WITHOUT THE EXTENSION> , <PROMPT TEXT OR COMPLIANT SSML GRAMMAR>

An Excel export to CSV format should be enough for rendering a compatible structure, ever since the text within a cell is dumped between quotes if it contains spaces. An example of a compliant file with SSML prompts would look like the following:

    sample_prompt_01,"<speak>Welcome to ACME. How can I help you today?</speak>"
    sample_prompt_02,"<speak>Press 1 for sales. <break time=200ms/>Press 2 for Tech Support. <break time=200ms/>Or stay in the line for agent support</speak>"
    ...

Additionally, prepare a YAML document with the structure mentioned in the setup.yaml file included in this repository. The fields are the following:

# CSV format is: FILE_NAME , PROMPT_CONTENT
csv_prompts_file: <my_csv_file.csv>

google_settings:
    # ROUTE TO THE JSON KEY ASSOCIATED TO GCP. IF THE ROUTE HAS SPACES, ADD QUOTES TO THE VALUE
    JSON_key: <my_key.json>

    # PROMPT TYPE. ALLOWED VALUES ARE:
    # normal | SSML
    prompt_type: SSML

    # FILE FORMAT. ALLOWED VALUES ARE:
    # wav | mp3
    output_audio_format: wav

    # COMPLIANT LANGUAGE CODE. SEE https://cloud.google.com/text-to-speech/docs/voices FOR COMPATIBLE CODES
    language_code: es-US

    # COMPLIANT VOICE NAME. SEE https://cloud.google.com/text-to-speech/docs/voices FOR COMPATIBLE NAMES
    voice_name: es-US-Wavenet-C

    # COMPLIANT VOICE GENDER. SEE https://cloud.google.com/text-to-speech/docs/voices FOR COMPATIBLE GENDERS WITH THE SELECTED VOICE ABOVE
    voice_gender: MALE

    # COMPLIANT AUDIO ENCODING. SUPPORTED TYPES ARE:
    # AUDIO_ENCODING_UNSPECIFIED | LINEAR16 | MP3 | OGG_OPUS
    audio_encoding: LINEAR16

3) Dependencies installation

Install the requirements in a virtual environment with the following command:

pip install -r requirements.txt

4) Inline calling

The usage of the script requires the following inline elements:

usage: init.py [-h] [-b BATCH] configurationYAML

Batch prompt generation with Google TTS services

positional arguments:
  configurationYAML     YAML file with operation settings

optional arguments:
  -h, --help            show this help message and exit
  -b BATCH, --batch BATCH
                        Amount of rows in the CSV file to process at the same
                        time. Suggested max value is 100. Default is 10

An example is:

py init.py setup.yaml

The command prompt will show logs based on the status of each row:

✅ Prompt sample_prompt_04.WAV created successfully!
✅ Prompt sample_prompt_01.WAV created successfully!
✅ Prompt sample_prompt_03.WAV created successfully!
✅ Prompt sample_prompt_02.WAV created successfully!

The corresponding audio files will be saved in the same location where this script is executed.

5) Encoding for Cisco CVP Audio Elements

Unfortunately, Google Text-To-Speech service does not support the compulsory 8-bit μ-law encoding as per the Python SDK documentation (I am currently working on a Java version which does support this encoding. This option might be released in the Python SDK in the future). However, there are many online services such as this one for achieving the aforementioned. Audacity can also be used for the purpose. Follow this tutorial for compatible file conversion steps. There's a more straightforward tool which has been proven useful for me in order to process batch files with the CVP compatible settings.

The resulting files can later be uploaded into the Tomcat server for usage within a design in Cisco CallStudio. The route within the CVP Windows Server VM is the following:

    C:\Cisco\CVP\VXMLServer\Tomcat\webapps\CVP\audio

Please refer to the Official Cisco Documentation for more information.

Crafted with ❤️ by Alfonso Sandoval - Cisco

Releases(v1.2.0)

v1.2.0(Aug 12, 2021)

Tested for 100 single-sentence concurrent records
Source code(tar.gz)
Source code(zip)

Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS)

TOPSIS implementation in Python Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) CHING-LAI Hwang and Yoon introduced TOPSIS

8 Dec 10, 2022

This python module is an easy-to-use port of the text normalization used in the paper "Not low-resource anymore: Aligner ensembling, batch filtering, and new datasets for Bengali-English machine translation". It is intended to be used for normalizing / cleaning Bengali and English text.

normalizer This python module is an easy-to-use port of the text normalization used in the paper "Not low-resource anymore: Aligner ensembling, batch

23 Nov 30, 2022

voice2json is a collection of command-line tools for offline speech/intent recognition on Linux

Command-line tools for speech and intent recognition on Linux

988 Jan 4, 2023

Ptorch NLU, a Chinese text classification and sequence annotation toolkit, supports multi class and multi label classification tasks of Chinese long text and short text, and supports sequence annotation tasks such as Chinese named entity recognition, part of speech tagging and word segmentation.

Pytorch-NLU，一个中文文本分类、序列标注工具包，支持中文长文本、短文本的多类、多标签分类任务，支持中文命名实体识别、词性标注、分词等序列标注任务。 Ptorch NLU, a Chinese text classification and sequence annotation toolkit, supports multi class and multi label classification tasks of Chinese long text and short text, and supports sequence annotation tasks such as Chinese named entity recognition, part of speech tagging and word segmentation.

186 Dec 24, 2022

A Python module made to simplify the usage of Text To Speech and Speech Recognition.

Nav Module The solution for voice related stuff in Python Nav is a Python module which simplifies voice related stuff in Python. Just import the Modul

1 Dec 20, 2021

Code for ACL 2022 main conference paper "STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation".

STEMM: Self-learning with Speech-Text Manifold Mixup for Speech Translation This is a PyTorch implementation for the ACL 2022 main conference paper ST

29 Oct 16, 2022

Code and datasets for our paper "PTR: Prompt Tuning with Rules for Text Classification"

PTR Code and datasets for our paper "PTR: Prompt Tuning with Rules for Text Classification" If you use the code, please cite the following paper: @art

118 Dec 30, 2022

easySpeech is an open-source Python wrapper for google speech to text API that doesn't require PyAudio(So you especially windows user don't have to deal with the errors while installing PyAudio) and also works with hugging face transformers

easySpeech easySpeech is an open source python wrapper for google speech to text api that doesn't require PyAaudio(So you specially windows user don't

14 May 24, 2022

Command Line Text-To-Speech using Google TTS

cli-tts Thanks to gTTS by @pndurette! This is an interactive command line text-to-speech tool using Google TTS. Just type text and the voice will be p

3 Nov 11, 2022

Utility for Google Text-To-Speech batch audio files generator. Ideal for prompt files creation with Google voices for application in offline IVRs

Related tags

Overview

Google Text-To-Speech Batch Prompt File Maker

1) GCP account setup

2) CSV and YAML files

3) Dependencies installation

4) Inline calling

5) Encoding for Cisco CVP Audio Elements

You might also like...

Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS)

This python module is an easy-to-use port of the text normalization used in the paper "Not low-resource anymore: Aligner ensembling, batch filtering, and new datasets for Bengali-English machine translation". It is intended to be used for normalizing / cleaning Bengali and English text.

voice2json is a collection of command-line tools for offline speech/intent recognition on Linux

Ptorch NLU, a Chinese text classification and sequence annotation toolkit, supports multi class and multi label classification tasks of Chinese long text and short text, and supports sequence annotation tasks such as Chinese named entity recognition, part of speech tagging and word segmentation.

A Python module made to simplify the usage of Text To Speech and Speech Recognition.

Code for ACL 2022 main conference paper "STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation".

Code and datasets for our paper "PTR: Prompt Tuning with Rules for Text Classification"

easySpeech is an open-source Python wrapper for google speech to text API that doesn't require PyAudio(So you especially windows user don't have to deal with the errors while installing PyAudio) and also works with hugging face transformers

Command Line Text-To-Speech using Google TTS

Releases(v1.2.0)

v1.2.0(Aug 12, 2021)

Owner

Ponchotitlán

Textlesslib - Library for Textless Spoken Language Processing

Bu Chatbot, Konya Bilim Merkezi Yen için tasarlanmış olan bir projedir.

This codebase facilitates fast experimentation of differentially private training of Hugging Face transformers.

A flask application to predict the speech emotion of any .wav file.

Client library to download and publish models and other files on the huggingface.co hub

An implementation of the Pay Attention when Required transformer

DAGAN - Dual Attention GANs for Semantic Image Synthesis

This repository contains all the source code that is needed for the project : An Efficient Pipeline For Bloom’s Taxonomy Using Natural Language Processing and Deep Learning

YACLC - Yet Another Chinese Learner Corpus

Using BERT-based models for toxic span detection

Dé op-de-vlucht Pieton vertaler. Wereldwijd gebruikt door meer dan 1.000+ succesvolle bedrijven!

STS Benchmark comprises a selection of the English datasets used in the STS tasks organized in the context of SemEval between 2012 and 2017. The selection of datasets include text from image captions, news headlines and user forums.

Reproducing the Linear Multihead Attention introduced in Linformer paper (Linformer: Self-Attention with Linear Complexity)

LewusBot - Twitch ChatBot built in python with twitchio library

SGMC: Spectral Graph Matrix Completion

Official code for "Parser-Free Virtual Try-on via Distilling Appearance Flows", CVPR 2021

Utilities for preprocessing text for deep learning with Keras

Code for the paper "Flexible Generation of Natural Language Deductions"

sangha, pronounced "suhng-guh", is a social networking, booking platform where students and teachers can share their practice.

Korean Simple Contrastive Learning of Sentence Embeddings using SKT KoBERT and kakaobrain KorNLU dataset