An automated workflow tool designed to synthesize multi-speaker conversational videos from structured transcript manifests, featuring synchronized voice audio and timed text overlays.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install conversation-video
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install conversation-video using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Conversation Video Generator?
The Conversation Video generator is a robust utility built to streamline the creation of spoken dialog media from textual input. By integrating synthetic multi-voice text-to-speech engine capabilities, developers can design immersive conversational flows with accurate timing profiles. This solution is categorized with other production-grade Openclaw Skills for high-efficiency media workflows, allowing users to map distinct speech styles, speaker labels, and custom layout positions directly from source data files.
The framework provides two rendering strategies. Teams requiring low overhead can employ a fast, dependency-free command-line path powered by ffmpeg. Developers needing rich transitions, dynamic typography, and pixel-perfect animations can leverage the React-based Remotion rendering pipeline. The combination of structural simplicity and aesthetic flexibility makes it an ideal choice for automated video creation.
Conversation Video Generator Use Cases
- Customer Discovery Audios & Videos: Transform raw feedback logs and user interviews into interactive visual chats for internal reviews.
- Programmatic Ads and Promos: Dynamically build localized conversation flows with custom branding and speaker voice maps.
- Podcast Subtitling and Audiograms: Automatically generate synced wave overlays and subtitles for podcast snippets.
- Interactive Social Media Content: Produce engaging dialogue-driven short videos using structured templates and text-to-speech components.
How Conversation Video Generator Works
- Transcript Compilation: Prepare a conversation JSON manifest detailing the speech blocks, actor labels, preferred voice profiles (e.g., M1-M5, F1-F2), and screen layout alignments.
- Audio and Timing Synthesis: Run the Python generator script to invoke the underlying TTS model. The script produces a combined master WAV file alongside an automated timings file (
output_timings.json) detailing accurate speech boundaries. - Video Composition: Select the rendering workflow. Compile quickly via ffmpeg drawing text commands, or copy the boilerplate to customize React-based animation components in Remotion.
- Final Export: Render and package the synced, high-quality MP4 movie assets ready for immediate playback and deployment.
Conversation Video Generator Setup
System Requirements
Ensure your development environment meets the following prerequisites:
- ffmpeg: Required on system path (or configure your environment to point to the correct execution binary).
- Python: Installed on your system with the required TTS generator tools.
- Node.js & npm: (Optional) Only necessary if using the Remotion visual rendering pipeline.
Step-by-Step Installation
- Install the required Python packages for multi-voice TTS speech generation:
pip install supertonic-tts
- Design a conversation manifest named
manifest.json:
[
{
"speaker": "NARRATOR",
"text": "Customer Discovery Interview",
"voice": "M1",
"speed": 1.0,
"align": "center"
},
{
"speaker": "INTERVIEWER",
"text": "Walk me through when you first realized...",
"voice": "M5",
"speed": 0.95,
"align": "left"
}
]
- Synthesize the voice sound assets and build timing JSON files:
python scripts/generate_audio.py manifest.json output.wav
- Generate the video with your preferred rendering path (e.g., ffmpeg):
python scripts/ffmpeg_render.py output_timings.json output.wav video.mp4
Conversation Video Generator Data Schema & Taxonomy
Transcript Configuration Schema
The input schema defines the narrative structure and voice models for generation:
| Property | Type | Description | Required |
|---|---|---|---|
speaker |
String | The actor label displayed alongside subtitles (e.g., NARRATOR, CUSTOMER). |
Yes |
text |
String | The actual spoken content to generate as audio. | Yes |
voice |
String | The designated TTS identifier (e.g., M1-M5, F1-F2). | Yes |
speed |
Float | (Optional) Speed scaling multiplier. Default is 1.0. |
No |
align |
String | Frame alignment placement for subtitles (left, right, center). |
Yes |
Asset Mapping Directory Structure
/scripts/generate_audio.py: Main entrypoint for speech synthesis and timing analysis./scripts/ffmpeg_render.py: High-efficiency CLI drawing renderer script./assets/remotion-boilerplate/: Ready-made React wrapper template for custom component design.
Conversation Video Generator Advanced Features
- Dual Rendering Engines: Provides quick programmatic conversion via CLI-ready drawtext filters or high-quality styled templates via a full-featured React framework.
- Responsive Alignment Mapping: Effortlessly configure bubble positions, visual colors, and margins matching speaker identity attributes inside central configuration maps.
- Dynamic Audio Timing Controls: Customize synthetic voice speeds and pause thresholds programmatically with automatic subtitle synchronization.
- Extendable Component Architecture: Leverage pre-designed Remotion patterns like word-by-word reveal highlights, dynamic audio visualizers, and customizable transitions, setting it apart from standard Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Go Like Hell
An executive-level AI agent skill that translates the legendary Ford-Ferrari motorsport rivalry into actionable business frameworks for handling competition, culture clashes, and high-pressure decision-making.
The Code Breaker
An executable AI knowledge companion that guides you through the science of CRISPR gene editing, patent competition, research dynamics, and the ethics of altering human DNA.
Space Economy Monitor
A specialized real-time intelligence engine analyzing the $1.7T global space economy, from SpaceX IPO prospects to orbital satellite constellations.
Humanoid Robot Tracker
The Humanoid Robot Tracker monitors and analyzes commercial deployments, supply chains, and investment rounds for the top 12 global humanoid robotics manufacturers.
Claw Test Skill
A streamlined, side-effect-free validation skill engineered to test and confirm direct API publishing workflows on the ClawHub registry.
Grok Code Review
A senior-level, security-first AI code review agent that audits codebases, pull requests, and implementation diffs following strict xAI standards.
Featured*
