This example app demonstrates how to use the Deepgram Text-to-Speech API with Python using Flask, a micro web framework for Python.
Deepgram is a voice AI company providing speech-to-text and language understanding capabilities to make data readable and actionable by human or machines.
Before you start, it's essential to generate a Deepgram API key to use in this project. Sign-up now for Deepgram and create an API key.
Follow these steps to get started with this starter application.
Go to GitHub and clone the repository.
Install the project dependencies.
pip install -r requirements.txtCopy the code from sample.env and create a new file called .env. Paste in the code and enter your API key you generated in the Deepgram console.
DEEPGRAM_API_KEY=%api_key%The main branch demonstrates a basic implementation, where text is sent to the API and an audio file response with synthesized text-to-speech is returned.
Checkout the other branches to see added functionality:
- output streaming: Demonstrates how to take advantage of Deepgram's output streaming feature. This example streams the audio response to the client as it is being generated.
git checkout output-streamingOnce running, you can access the application in your browser at http://127.0.0.1:5000
python app.pyIf you have found a bug or if you have a feature request, please report them at this repository issues section. Please do not report security vulnerabilities on the public GitHub issue tracker. The Security Policy details the procedure for contacting Deepgram.
We love to hear from you so if you have questions, comments or find a bug in the project, let us know! You can either:
- Open an issue in this repository
- Join the Deepgram Github Discussions Community
- Join the Deepgram Discord Community
This project is licensed under the MIT license. See the LICENSE file for more info.