Actions25
- Sound Actions
- Speech Actions
- File Actions
- Transcription Actions
- Video Actions
- Add Audio to a Video
- Add Audio with Subtitles to a Video
- Add Subtitles to a Video
- Add Subtitles to a Video From a File
- Add Watermark to a Video
- Blur a Video
- Clip a Video
- Create a Slideshow
- Crop a Video
- Extract Audio From a Video
- Frame a Video
- Generate a Video
- Get a Specific Video
- Mute a Video
- Rotate a Video
- Split a Video Into Scenes
Overview
The "Generate a Video" operation in this node allows users to create videos programmatically by combining text-to-speech synthesis, audio files, and visual scenes. It supports specifying video resolution, voice for speech synthesis, subtitles with customizable styles, and audio integration. This node is beneficial for automating video content creation such as marketing videos, educational content, social media clips, or slideshows with narration.
Practical examples include:
- Generating a narrated video from a script where the text is converted into speech using a selected voice.
- Creating a slideshow video with multiple images and background audio.
- Adding styled subtitles synchronized with the audio for accessibility or emphasis.
Properties
| Name | Meaning |
|---|---|
| Name | The name of the video to be generated. |
| Resolution | The video resolution and orientation. Options include: Horizontal (1080p HD, 1440p 2K, 2160p 4K), Vertical (1080p HD, 1440p 2K, 2160p 4K), Square (1080p HD, 1440p 2K, 2160p 4K). |
| Text | The text input that will be converted into speech synthesis for the video narration. |
| Voice | The voice used for speech synthesis. Multiple voice options are available, including names like Alberto, Alexandra, Echo, etc. |
| Audio URL | A public downloadable URL of an audio file to add to the video. |
| Trim Audio | Whether to trim the audio to match the video length if the audio is longer than the video. |
| Volume | Sets the audio volume percentage from 1% to 100%, where 100% is original volume. |
| Scenes (JSON) | JSON array defining multiple scenes for the video or slideshow. Each scene includes asset source, type (e.g., image), duration, and effect. |
| Subtitle - Style | Subtitle style options such as Simple, Signal, Rainbow, Highlight Current Word, and combinations thereof. Default is "Highlight Current Word". |
| Subtitle - Language | Language code for subtitles, e.g., en (English), fr (French), es (Spanish), etc. |
| Subtitle - Font Family | Font family for subtitles, e.g., Arial, Lobster, Roboto, Korean, Chinese Simplified, etc. Default is Arial. |
| Subtitle - Font Size | Font size for subtitles, numeric value between 1 and 100. Default is 20. |
| Subtitle - Word Color | HEX color code for subtitle words, e.g., #FEEE15 (Yellow). |
| Subtitle - Line Color | HEX color code for subtitle lines, e.g., #FFFFFF (White). |
| Subtitle - Line Words | Number of words displayed at a time in subtitles, between 1 and 10. Default is 4. |
| Subtitle - Outline Width | Width of the subtitle outline, numeric between 1 and 100. Default is 5. |
| Subtitle - Position | Position on the video where subtitles appear, e.g., Top Left, Bottom Center, Mid Bottom Center, etc. Default is Mid Bottom Center. |
| Subtitle - Orientation | Text direction for subtitles: Left to Right or Right to Left. Default is Left to Right. |
| Wait for Completion | If enabled, the node waits until the video generation is complete before returning the full video object; otherwise, it returns only the video ID and creation timestamp immediately. |
| Webhook URL | Optional URL to receive webhook notifications about video processing status, including video ID and URL. |
Output
The node outputs a JSON object representing the generated video. When waiting for completion, this includes detailed video metadata such as the video URL, ID, creation timestamp, and possibly other attributes returned by the API. If not waiting, the output contains minimal information like the video ID and creation timestamp.
If the node handles binary data (e.g., video files), it would typically provide a binary property containing the downloadable video content or a link to it. However, based on the provided information, the output focuses on JSON metadata and URLs rather than direct binary data.
Dependencies
- Requires an API key credential for authenticating with the external video generation service.
- Depends on the Bookoly API endpoints hosted at
https://bookoly.com/api/v1. - Network access to the Bookoly API and any specified audio URLs must be available.
- Proper configuration of the API authentication credential within n8n is necessary.
Troubleshooting
Common Issues:
- Invalid or missing API credentials will cause authentication failures.
- Incorrect or inaccessible audio URLs may result in errors when adding audio.
- Improperly formatted JSON for scenes can cause parsing errors.
- Selecting unsupported voices or languages might lead to API rejections.
- Not waiting for completion while expecting full video details can cause confusion.
Error Messages:
"No handler found for video.generateVideo"indicates a misconfiguration or missing implementation for the requested operation."Failed to execute generateVideo: <error message>"suggests an error during API interaction or parameter validation.
Resolutions:
- Verify API credentials and permissions.
- Ensure audio URLs are publicly accessible and downloadable.
- Validate JSON syntax for scenes input.
- Choose supported voices and languages from the provided options.
- Enable "Wait for Completion" if you need the full video object after processing.
Links and References
- Bookoly Official Website
- Bookoly API Documentation (assumed base URL for API calls)
- n8n Documentation on Creating Custom Nodes