Simpler Text to Speech API

Apr 13, 2022

Narakeet now has one of the largest online collections of realistic text to speech voices, and we’ve been hearing from many of our users that they would like to use the text to speech capabilities of Narakeet but within their software. Today, we’re making it much easier to automate audio production, using our simplified streaming API.

Although Narakeet had a developer API from the early days, it was optimised for large content, long conversions suitable for video contents. Audio projects can be a lot simpler. Instead of a long and complicated process of requesting build jobs, then polling our storage, the simplified streaming API helps you achieve everything with just one request.

To use the streaming API instead of the old polling API, just tell Narakeet you want back a data stream using the accept header, and set it to application/octet-stream.

Here is an example of a request that will create a M4A file from a short piece of English text, and save it to result.m4a.

curl -d "Hi there, this is your API speaking" -H 'Content-Type: text/plain' -H "x-api-key: $APIKEY" -H "accept: application/octet-stream" --output result.m4a https://api.narakeet.com/text-to-speech/m4a 

The streaming API is limited to requests of 1KB, and compressed output. For more information, check out the Text to Speech API page.