Access Unlimited* text-to-speech for your Shotstack videos with the Create API 🎉

We are thrilled to announce a significant advancement in Shotstack’s capabilities - the introduction of generative AI with our groundbreaking Create API. The best part? The Create API is now included in all paid subscriptions at no extra cost!

This launch marks a transformative phase in our journey to redefine the landscape of video creation. Our ambition is to equip you with cutting-edge tools that help you create captivating videos at scale, all under one roof.

So, what does the Create API mean for you?

Starting today, paid subscribers will have unlimited* access to Shotstack’s text-to-speech functionality. This allows you to add text-to-speech to as many Shotstack videos as your subscription covers. You can upgrade your subscription here.

If you’re a customer of ElevenLabs, D-ID, or HeyGen, you can integrate their text-to-speech and text-to-avatar features directly into Shotstack, for even more creative videos.

We are dedicated to providing you with the latest and most advanced tools you need to shape the future of video. We look forward to seeing the amazing content you will produce with the Create API!

While this first release is focused on the API and developers, future releases will focus on enabling anyone to use Create to include generative AI in their videos, at scale.

The Create API is now included in paid Shotstack subscriptions. So why wait? Upgrade your subscription or get a head start by viewing the API documentation, and let the creativity flow!

*Please note, a fair use policy applies.

Thanks for this - however, I am not sure what the Elevenlabs integration does (i currently use them - but not sure how it fits into shotstack)

1 Like

Can you share some example videos or use-cases using text-to-speech? This might help to provide some inspiration…

1 Like

Great suggestion and here are a few use cases to help spark inspiration:

Programmatically turn long form articles to video at scale

This is great for publishers, media owners, education providers or anyone with a high volume of text articles they want to easily turn into a video.

We have an example video here Shotstack Example: Automating video creation from a long form text article - YouTube

For this use case, we took a long form text article, used GPT4 to summarise the key points and write a script, the Create API was used to automatically generate the voiceover - in this instance in Portuguese, the Edit API was then used to build the video, which included bringing in stock imagery, however this could be existing image or footage assets you already have.

Automated Voice Overs

You can use the Create API to automatically add a voiceover to any of your videos, removing the need (and expense) to hire a voiceover artist. Not only do voiceovers add an extra element to your videos, they also make your videos more accessible so you can reach a wider audience.

For example, automotive or real estate companies could use text-to-speech to narrate car walkarounds or property walk throughs.

Automated Translations

You can automatically translate your voiceover into over 30 languages, with the Shotstack text-to-speech functionality. This is ideal for anyone with an audience or customers in multiple markets, it’s a quick (and cost effective) way of increasing engagement and relevance with each of your audience members.

With this use case, you could repurpose existing videos you have and make them available in new markets or to new audiences.

These are just a few examples of how you could use text-to-speech in your video creation.

We’d love to hear from the Shotstack community as well about how they are planning to use, or are already using, text-to-speech in their video creation.

The ElevenLabs integration lets you call ElevenLabs directly from Shotstack to generate an audio voice over from text. The audio file will be generated by ElevenLabs and returned and saved to Shotstack when ready. The file URL can then be used in your Shotstack Edit.

If you already have files created in Elevenlabs, you can continue to use these directly in your Shotstack Edit, outside of the Create API.

It’s unfortunate that the Text to Speech API does not support the Vietnamese language. Hopefully, it will be integrated in the near future.