OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Image & Video AI

AI Mixed Cut

AI Mixed Cut is a documented desktop-workflow prototype for analyzing authorized media, organizing reusable content in JSON libraries, drafting scripts, generating speech and subtitles, and composing videos for human review. The repository contains workflow documentation and interface screenshots, not the complete implementation.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

AI Mixed Cut — OpenViST project profile in Image & Video AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use the repository as a workflow reference when designing or assessing a human-reviewed process for repurposing authorized source media; it does not provide the full application implementation.

Who it is for

  • Content operations teams managing large archives of existing media.
  • Editors splitting longer material into themed content.
  • Product and technical teams assessing an AI-assisted repurposing workflow.

Documented uses

  • Organize extracted content into editable libraries of topics, narrative frameworks and reusable quotations.
  • Combine library items into candidate scripts for editorial review.
  • Plan narration and aligned subtitles as part of a video-production workflow.
  • Specify clip order, duration, transitions and visual treatments for composed videos.
Before you choose

Requirements & limits

The repository is public and lists an MIT license, but states that the complete implementation code is not published. The documented desktop workflow targets Windows.

  • The project is a workflow case and prototype presentation, not a complete working application.
  • The described library uses editable JSON files for topics, frameworks and quotations.
  • Edge TTS is described for speech generation and aligned SRT output; the repository does not provide the complete implementation or test evidence.
  • The composition design includes configurable clip ordering and duration, visual effects, xfade transitions, batch tasks and optional NVIDIA NVENC acceleration.
  • Source materials must be authorized, and generated content is intended for human review.

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

Organize authorized source material into a reusable content library

Structure extracted source content into editable JSON files for later workflow stages.

Before you start

  • Text and timing information extracted from source material that you are authorized to use and adapt.

Steps

  1. Retain the source information alongside extracted editable text and timing details for traceability and review.

  2. Identify topics, including core subject, intended audience, and value proposition, and record them in topics.json.

  3. Abstract narrative structures and content organization into frameworks.json, and save reusable quotations in golden_sentences.json.

  4. Review and edit the JSON library as needed; it is described as independently readable and suitable for manual changes and version management.

Expected outcome

A traceable, editable JSON library organized by topics, frameworks, and reusable quotations.

Guide limitations

  • The repository provides workflow documentation and interface screenshots, not complete implementation code.
  • Use only material with legal rights for use and adaptation.
Documentation 1 ↗
Source-based practical guide

Prepare candidate scripts, speech, and subtitles from a material library

Use organized material as the documented input for draft script, narration, and subtitle stages.

Before you start

  • A material library containing topics, frameworks, and reusable quotations.
  • Authorized source material; generated content must receive human review.

Steps

  1. Combine a topic, framework, and quotation from the library under defined content constraints to produce a candidate script.

  2. Treat generated titles and tags as drafts and review them before use.

  3. Use the documented Edge TTS integration to synthesize multilingual speech, with speech-rate, pitch, and volume controls; generate time-aligned .srt subtitles alongside the audio.

  4. Review subtitle line breaks and retain intermediate files so they can be edited before later workflow stages.

Expected outcome

Candidate script material, synthesized narration, and time-aligned subtitle files prepared for human review and potential later video composition.

Guide limitations

  • The repository does not publish the complete implementation, and it provides no complete implementation or test evidence for the Edge TTS integration.
  • AI-generated content requires factual, copyright, and brand review; titles and tags are drafts.
  • Only use text, audio, and video material that you are authorized to use.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
toki-plus/ai-mixed-cut · Official homepage title · retained in its source language
How we review sourcesSuggest a correction