Multimodal Story
A 4-step recipe with Hyperbolic. We can help you get access.
Recipe · 4 steps
Multimodal Story
with Hyperbolic
Generate a story, illustrate it, and narrate it in one pass.
- List the live inference catalog so the chat and image models can be confirmed before generation begins.
- Ask the chat model to write a short, self-contained story based on the theme.
- Render a cover illustration using the story text as the diffusion prompt.
- Convert the story to speech audio and capture the base64 audio and its duration.
What you'll need to have ready
- apiKey: Hyperbolic API key passed as a Bearer token.
- chatModel: Chat model id used to write the story.
- imageModel: Image model name used to render the cover (e.g. SDXL1.0-base).
- theme: The theme or premise for the short story.
- language: TTS language code for narration.
- speed: Speech speed between 0.5 and 2.0.
For your developer
Arazzo workflow hyperbolic-ai:multimodal-story, 4 operations: listModels → createChatCompletion → generateImage → generateAudio. Specs on APIs.io.