Build AI Generated Podcasts 3 - Batch Job & API Setup
In Part 3 of the AI-powered podcast series, we’ll be setting up the batch job for generating podcast audio and building an API to submit these tasks. You’ll see how to configure and process audio generation jobs with Suno’s Bark model while also setting up the API to interact with this batch job.
We'll cover how to handle audio generation asynchronously, how to define necessary resources, and why we set permissions in certain ways. By the end of this video, you'll have a fully working batch job and API to generate text-to-speech audio based on podcast content.
If you missed Part 1 and Part 2, be sure to go back and watch them first to get the full project setup and resource definitions!
- Part 1: Python Project Setup
- Part 2: Create Resources
Resources
- Project Code: https://github.com/nitrictech/ai-podcast
- Nitric Docs: https://nitric.io/docs
- Install Nitric: https://nitric.io/docs/get-started/installation
- Suno's Bark Model: https://github.com/suno-ai/bark
- UV Python Package Manager: https://github.com/astral-sh/uv
- See the list of available voice presets: https://suno-ai.notion.site/8b8e8749ed514b0cbf3f699013548683?v=bc67cff786b04b50b3ceb756fd05f68c
Stay Connected
- 🌐 Learn more and explore the Nitric docs: https://nitric.io
- ⭐️ Support us on GitHub by starring the Nitric repository: https://github.com/nitrictech/nitric
- 🧑💻 Join our community on Discord: https://nitric.io/chat
- 🔔 Don't forget to like, comment, and subscribe to our YouTube channel! https://www.youtube.com/@nitric_io