Shotstack allows you to create thousands of bespoke, data-driven videos in minutes. We've incorporated some of the world's most advanced AI models so you can create even more compelling videos, at scale.
Automatically translate and localise your content by adding voice-overs in over 30 languages. Reduce costs and save time with unlimited* text-to-speech functionality on any of Shotstack's paid plans.
* Fair use policy applies.
It would have taken a lot of research on what technologies we needed to leverage technically for us to achieve the desired outcome. This would have taken at least two months of engineering time for a simple use case, and up to 6 months if the scope widened.
Automatically add a voice over or narration to your video with text-to-speech. Simply add your script and the technology will do the rest. And the best bit? It's available in over 30 languages. So you can take one generic video and automatically version it for multiple languages at the same time.
Give your videos an additional layer of personalisation by automatically adding avatars at scale. The Create API has integrations in place with D-ID and HeyGen, so you can use your API keys to bring your existing avatars to the videos you are building with Shotstack.
Generate images from text using the power of AI. The Create text to image API allows you to generate images from a text prompt. Use the latest Stable Diffusion models from Stability AI and customise the output to your needs.
Using the latest GPT-4 model from OpenAI, the Create API allows you to generate text from a text prompt. Perfect your script, summarise news and content, or create persuasive and engaging copy for your videos.
Bring it all together by combining AI generated voice overs, avatar videos, images and text in to a video using the power of the Create API.
