AI tools have risen in prominence largely due to text-based LLMs and their impressive capabilities (e.g. ChatGPT). As such, text-based workflows dominate much of the AI discourse, but other AI modalities, like image, video, and audio generation are fast becoming high-quality and extremely powerful.
In this tutorial, we’ll walk through some helpful AI audio-generation workflows with the platform ElevenLabs, a leader in the AI audio space. You’ll learn how to use their text-to-speech model to:
- Convert blog posts into podcasts
- Generate sound effects from prompts for videos
- Translate your audio and video content into 29 different languages with AI dubbing
You’ll need:
- ElevenLabs account