Product Update: Text-to-Speech and Transcription Updates

We normally announce new features in a single monthly update, but there’s a couple that we just couldn’t resist sharing with you before the busy holiday season.

Noor Hammad • Wed 25 November, 2020

We normally announce our new product features in a single monthly update, however there’s a couple that we just couldn’t resist sharing with you before the busy holiday season.

So here’s your second update for November. If you missed our previous one check it out to learn about Whooshkaa Cloud Studio.

Text-to-Speech

Text-To-Speech has been available on Whooshkaa Custom plans for a couple of years. This update adds some new capabilities and makes the process of generating a text-to-speech episode available to all podcasters.

The Basics

As the name suggests, Text-To-Speech turns text into synthesised speech.

AI powered voices create realistic sounding speech, which can be saved as audio files in your Whooshkaa Media Library or added directly to Episodes.

There are 29 supported languages with a range of dialects and voices available for each.

You supply your text by copying and pasting into Whooshkaa or configuring a feed which can fetch JSON data from an API (more on that below).

There are options to customise the voice by setting the volume, speed and pitch.

Text-to-Speech Customisation Settings

When you’re ready you click “Create” and Whooshkaa will drop the audio file into the Media Library Folder / Episode of your choice.

Automate The Process

This one’s for the developers out there…

You can configure Text-To-Speech jobs to run on a schedule and when combined with Data Feeds, you have a powerful solution for automating the creation of podcast content.

Data feeds allow you to specify one or more sources of text, received as JSON, typically by fetching from an API.

A templating engine allows you to specify which data should be turned into speech.

Whooshkaa will fetch the data from your feed, extract the specified text, turn it into speech and save it to your Media Library or create a new Episode in your Show.

Available Now

Text-To-Speech is available on Semi-Pro, Pro and Business plans. Check the Plans & Billing page in the Whooshkaa Dashboard for more details on entitlements.

Transcription Updates

Whooshkaa Transcripts has been updated to allow multi-speaker formatting.

On Semi-Pro you can edit your Transcripts to label sections with a speaker’s name.

On Pro and Business plans, Advanced Transcripts now uses machine learning to identify and label each speaker during the transcription process.

To use multi-speaker identification, select the “Enable speaker identification” option when creating a transcript. Specifying the number of speakers helps Whooshkaa more accurately identify speakers.

Multi-Speaker Transcription

Send us your feedback

As always we’d love to hear how we can continue to help you on your podcasting journey. Got some feedback? Drop us a line through the Whooshkaa Support Portal.

Read this next...

Product Updates

Product Update: November 2020

Blog post image: Product Update: November 2020

Whooshkaa Cloud Studio provides podcasters with an easy-to-use recording and editing solution that requires nothing more than a web browser.

3 Nov 2020