This repository provides a quick example demonstrating how to access the Narakeet streaming Text to Speech API from Python.
The example sends a request to generate audio from text and saves it output.m4a
in the local directory.
The example uses the requests python library to send HTTPS requests to the Narakeet API.
Note that Narakeet also has a text to speech API to generate long content, suitable for larger conversion tasks. See the Long Content Text to Speech API Example for more information on how to use that.
To use this example, you will need Python (3.7 or more recent), and an API key for Narakeet.
- edit tts.py and add your API key on line 1, instead of the value
'YOUR_API_KEY_HERE'
. You can optionally modify the voice and text parameters on lines 2 and 3, which control the text to speech synthesis voice and the text sent to the API for synthesis. - run
pip install -r requirements.txt
to install the required libraries - run
python tts.py
to create the output audio.
Check out https://www.narakeet.com/docs/automating/text-to-speech-api/ for more information on the Narakeet Text to Speech API