Visual Storybook / Animated Audiobook

English Text to Multi-Language Narrated Video

Powered by Qwen3.5-Omni-Plus (narration) + HappyHorse 1.0 (video)

Upload English text and generate a narrated video storybook:

  • AI generates cinematic video scenes from your story
  • Professional narration in 36 languages (preset or cloned voice)
  • Each scene gets its own video + synchronized audio
  • All scenes assembled into one final MP4
Component Model What it does
Narration Qwen3.5-Omni-Plus Translates + speaks the story
Video HappyHorse 1.0 Generates cinematic scene videos
Scene Prompts Qwen3.5-Omni-Plus Auto-creates video prompts from text

Pipeline: Text > Split into scenes > Qwen generates video prompts > HappyHorse generates video per scene > Qwen narrates audio per scene > FFmpeg composites video+audio > Concatenates all scenes into final MP4

API Keys needed: DASHSCOPE_API_KEY (audio) + HAPPYHORSE_API_KEY (if using happyhorse.app) or just DASHSCOPE_API_KEY for both audio and video (DashScope provider)

Built with Gradio | Narration by Qwen | Video by HappyHorse 1.0