Guidelines for Using Script-to-Video API

Visla’s API makes it easy to create videos from text-based scripts. Follow these concise guidelines to get started quickly.

Video Description

An optional API parameter is video description, which offers control over the following:

  1. Pacing: Control plain text script scene length by specifying video pacing (see examples below). Visla AI uses pacing to guide scene splitting. Default: Moderate Note: pacing control is omitted if the script contains scene markers or scene settings.
  2. Aspect Ratio: Specify the video aspect ratio or platform, such as "Make a fast-paced TikTok video" or "Make a 9:16 video." The default aspect ratio, if unspecified, is 16:9. Supported values: 16:9, 9:16, 1:1
  3. Background Music (BGM): Influence the background music selection. For example: "Use a calm background music track". If not mentioned, the default is for the AI to decide BGM based on the video's content and type.

Use natural language to describe the target video you want to create, as it is a prompt-like parameter. Examples:

  1. "Fast-paced video for TikTok. Dynamic transitions and vibrant pacing."
  2. "Moderate-paced video for a corporate audience with upbeat yet formal background music."
  3. "Video Pacing: slow. Aspect Ratio: 1:1"

Script

Plain Text for Visla AI-Controlled Scene Lengths

Let Visla AI manage scene lengths and pacing by providing a plain text narration script.


At SmartStream, we understand the importance of water safety and compliance. Our AI-driven platform empowers 120Water with personalized content that tells your unique story and provides powerful sales material. Imagine your sales team equipped with precise messaging, tailored to each prospect. Our platform simplifies the process of maintaining clear and effective messaging across diverse product lines and market verticals. With SmartStream, managing content becomes effortless, ensuring your sales team always has access to the most current and effective messaging tools. SmartStream enhances your sales performance by providing AI-powered coaching and response management. Our platform continually learns from interactions and outcomes, allowing your messaging strategies to evolve based on what works best for engaging your specific audience.

Pacing Options vs. Scene Length:

  • Fast pace: Quick transitions, 3-5 seconds per scene.
  • Moderate pace: Balanced pacing, 5-10 seconds per scene.
  • Slow pace: In-depth storytelling, 10-20 seconds per scene.

Scripts with Scene Markers

Control scene durations and structure explicitly with scene markers. Scene length is determined by AI voice narration at approximately 20-25 words per 10 seconds.


[Scene 1]

[Narrator]: At SmartStream, we understand the importance of water safety and compliance.

[Scene 2]

[Narrator]: Our AI-driven platform empowers 120Water with personalized content that not only tells your unique story but also provides powerful sales material.

[Scene 3]

[Narrator]: Imagine your sales team equipped with precise messaging, tailored to each prospect.

[Scene 4]

[Narrator]: Our platform simplifies the process of maintaining clear and effective messaging across diverse product lines and market verticals.

[Scene 5]

[Narrator]: With SmartStream, managing content becomes effortless, ensuring your sales team always has access to the most current and effective messaging tools.

[Scene 6]

[Narrator]: SmartStream enhances your sales performance by providing AI-powered coaching and response management.

[Scene 7]

[Narrator]: Our platform continually learns from interactions and outcomes, allowing your messaging strategies to evolve based on what works best for engaging your specific audience.

Adding Visual Cues to Guide Stock Footage Selection

📘

To influence stock footage selections, include visual cues in your script. Visual cues can consist of a visual description (a short sentence), tags, or a combination of both. Tags will be used for keyword search (exact phrase match), and the visual description will be used for semantic search (synonym match) of the stock footage (both public stock and private stock).

For API developers using Visla private stock, this approach provides robust control over footage mapping. Developers can manage both sides: fine-tune the labels for private stock footage and specify the visual cues in the script. This dual control ensures precise alignment with project requirements.

For public stock footage (e.g., Getty, Storyblocks), this method is still effective but offers less control because developers cannot modify stock labels. When specifying visual cues, be aware that an exact matched footage may not always be available, especially with public stock footage. This can sometimes result in less ideal footage selections compared to allowing the AI to take control by omitting the visual cues.


[Scene 1]

[Visual Cues]: Tags: modern office, teamwork, data analysis, technology

[Narrator]: At SmartStream, we understand the importance of water safety and compliance.

[Scene 2]

[Visual Cues]: A presentation showing a customized AI-driven platform interface with the 120Water logo, focusing on a clean and modern design. Tags: presentation, software interface, corporate branding

[Narrator]: Our AI-driven platform can empower 120Water with personalized content that not only tells your unique story but also provides powerful sales material.

[Scene 3]

[Visual Cues]: Tags: team discussion, charts, whiteboard collaboration

[Narrator]: Imagine your sales team equipped with precise messaging, tailored to each prospect.

[Scene 4]

[Visual Cues]: Tags: dashboard, content management, real-time updates

[Narrator]: Our platform simplifies the process of maintaining clear and effective messaging across diverse product lines and market verticals.

[Scene 5]

[Visual Cues]: A confident sales representative presenting to a group of clients with synchronized messaging displays in a polished conference room. Tags: sales presentation, client meeting, messaging tools

[Narrator]: With SmartStream, managing content becomes effortless, ensuring your sales team always has access to the most current and effective messaging tools.

[Scene 6]

[Visual Cues]: Tags: AI analytics, customer interactions, data insights

[Narrator]: SmartStream enhances your sales performance by providing AI-powered coaching and response management.

[Scene 7]

[Visual Cues]: A graph showing steady improvement in audience engagement metrics over time with clean, professional animation.

[Narrator]: Our platform continually learns from interactions and outcomes, allowing your messaging strategies to evolve based on what works best for engaging your specific audience.

Visual Tag Examples:

  • "modern office, teamwork, data analysis."
  • "Presentation, software interface, corporate branding."
  • "Sales team discussion, charts, whiteboard collaboration."