OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Chat & Assistants

Gptauthor

Gptauthor is a Python command-line application that uses an AI model to turn a YAML story prompt into a chapter-by-chapter synopsis and long-form story draft. Writers can review or revise the synopsis before the tool generates chapters, which draw on the synopsis and the preceding chapter. It saves the resulting story in Markdown and HTML.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Gptauthor — OpenViST project profile in Chat & Assistants.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you have a story brief and want a structured synopsis-review-draft workflow rather than a single short response to a prompt.

Who it is for

  • Writers developing a novel or other long-form fiction from an outline, characters and style notes
  • Screenplay writers who want to draft a longer story from a structured prompt

Documented uses

  • Turn a story description into a synopsis with a chosen number of chapter summaries
  • Review or revise a story plan before drafting chapters
  • Generate a sequential multi-chapter story and save it in Markdown and HTML
Before you choose

Requirements & limits

The project is publicly available on GitHub under the MIT license. It can be installed with pip or used through a supplied Google Colab notebook. The documented command-line example requires an OpenAI API key; model usage may have provider charges.

  • The synopsis is presented for review before chapter generation, allowing changes to the plan at that stage.
  • The documented workflow uses an OpenAI model and requires an API key; model selection and generation settings can be supplied as command-line options.
  • The output is written as Markdown and HTML in an output directory.
  • The README mentions a localhost model option without documenting how to configure that setup.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Generate a multi-chapter story from a prompt

Use GPTAuthor’s command-line example to draft a three-chapter story and save its output.

Before you start

  • Install GPTAuthor with pip; a Python virtual environment is recommended.
  • Set an OpenAI API key in the local environment.
  • Use the example YAML story prompt, or prepare a YAML file defining the story and prompts.

Steps

  1. Install the tool with the command below.

    Documented command
    pip install gptauthor

  2. Set OPENAI_API_KEY in the shell: on macOS/Linux, use export OPENAI_API_KEY=sk-; on Windows, use setx OPENAI_API_KEY "sk-".

  3. Run gptauthor --story prompts-openai-drama --total-chapters 3 --llm-model gpt-5.4-mini --llm-temperature 0.1.

  4. Review the generated synopsis and optionally revise it; proceed when satisfied. GPTAuthor then writes chapters iteratively using the synopsis and preceding chapter.

Expected outcome

GPTAuthor writes the story as Markdown and HTML under `./_output/`; the README describes output subfolders organized by prompt file, model, and run details.

Guide limitations

  • The example requires an OpenAI API key; the README also lists a localhost option but does not document its setup.
  • The synopsis requires human review before the story-writing stage proceeds.
  • Model speed, quality, and cost can vary; the README notes that higher-cost GPT-4 models may be slower.
Documentation 1 ↗Documentation 2 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
dylanhogg/gptauthor · Official homepage title · retained in its source language
How we review sourcesSuggest a correction