Features

AiToVid is packed with powerful features designed to make video creation simple and efficient.

PowerPoint to Video Conversion

Upload your PowerPoint presentations (.pptx) and optionally a PDF export for the highest quality output. AiToVid automatically extracts your slides and prepares them for narration. Projects can contain up to 50 slides.

AI Script Generation

Our AI analyzes your slide content and generates compelling narration scripts automatically. The AI considers:

• Text content on each slide
• Your goal statement and target audience
• Any custom context you provide

Scripts can be generated in bulk or regenerated individually, and you have full control to edit them as needed.

High-Quality AI Voices

Choose from a diverse library of natural-sounding AI voices powered by ElevenLabs. Select your preferred voice when creating a project, or change it later in the project settings. Every voice is designed to sound professional and engaging.

Manual Voice-Over Recording

Need to use your own narration? Open any slide card and click the microphone button to launch AiToVid’s built-in recorder. You can capture up to 5 minutes of audio per take, preview it immediately, re-record as often as you like, and then upload it straight to the slide without leaving the editor.

• Match your AI voice: Enable the “Match selected project voice” toggle to run the recording through ElevenLabs speech-to-speech so it sounds like the same AI actor you chose for the project.
• Transparent pricing: Voice conversion costs 6 tokens per minute, rounded up to the next minute. The recorder displays the estimated cost (e.g., a 95-second clip = 2 minutes = 12 tokens) before you upload.
• Token safeguards: Tokens are only deducted if conversion is enabled. If you do not have enough tokens, the upload is blocked and you can either disable conversion or top up your balance.
• Automatic limits: Recordings auto-stop at 5 minutes, and a warning badge appears once you pass 4 minutes so you can wrap up your read.

Prefer to polish audio elsewhere? Use the Upload audio action on any slide to import a finished WAV/MP3 and optionally run it through the same conversion workflow above.

Custom Pronunciation Guides

Ensure that your brand names, technical terms, and acronyms are pronounced correctly. You can:

• Create reusable pronunciation guides for consistent usage across projects
• Add custom pronunciation rules when creating a new project
• Preview how words will sound before generating audio

Slide-by-Slide Control

Maintain full control over your content. In the project editor, you can:

• Edit scripts for each slide with a built-in text editor
• Regenerate scripts for individual slides or all slides at once
• Play audio for each slide to review narration
• Regenerate audio for individual slides or all slides
• Upload custom audio files for any slide
• Replace slide images if needed
• Insert new slides or delete existing ones
• Reorder slides with drag-and-drop controls

Background Processing with Real-Time Updates

AiToVid handles intensive operations in the background so you can continue working:

• Script generation uses background jobs with real-time progress updates
• Audio generation is processed asynchronously with live status tracking
• Video export happens in the background with progress indicators
• All operations publish updates via server-sent events for instant feedback

Project Collaboration

Work together with your team:

• Invite collaborators to your projects via email
• Role-based permissions (Owner, Editor, Viewer)
• Pending invitations management
• Share projects securely with specific users

Project Management

Keep your work organized with our intuitive project dashboard:

• View all your projects with progress indicators
• See project status at a glance (Draft, Narration, Review, Ready, Completed)
• Duplicate projects to reuse configurations
• Delete projects you no longer need
• Download completed videos with one click

Project Groups & Tagging

• Groups: Every project card now includes a Manage Group action (••• menu). Assign a project to an existing group, create new color-coded groups, edit descriptions, or remove a group entirely (affected projects automatically return to the “Projects” section). On the dashboard, each group renders as a collapsible section so large workspaces stay tidy.
• Tags: Use the Tags panel on each project card to add multiple descriptive tags. You can create, rename, recolor, and delete tags from the same modal, then reuse them across projects.
• Filtering: The dashboard includes a Filter by tags control that supports multi-select. Apply as many tags as needed to narrow the grid, and click any active chip to remove it or use “Clear filters” to reset.

Language Dubbing (Preview)

AiToVid can create a full multilingual copy of any project — with translated scripts and a new AI voice — using the Language Dubbing feature.

How to Create a Language Variant

1. Open a project that already has scripts generated.
2. Click the Language Versions button in the project header.
3. Click Add Language, choose your target language and an AI voice for that language, then click Create.
4. AiToVid will translate all scripts automatically (2 tokens per slide, charged at creation).

Workflow States

Viewing and Editing Variants

Language variants appear in the project dashboard nested under the source project. Open the dropdown to switch between the base project and its variants. You can edit the translated scripts before generating audio.

Token Costs

• Translation: 2 tokens per slide, charged when the variant is created
• Audio: 3 tokens per slide, billed when audio is generated (same as subsequent audio regenerations on base projects)

Supported Languages

Arabic, Bulgarian, Chinese, Croatian, Czech, Danish, Dutch, English, Filipino, Finnish, French, German, Greek, Hindi, Indonesian, Italian, Japanese, Korean, Malay, Polish, Portuguese, Romanian, Russian, Slovak, Spanish, Swedish, Tamil, Turkish, and Ukrainian (29 languages via ElevenLabs Multilingual v2).

Limitations

• One variant per language per project
• The pronunciation guide is copied from the source project at creation time; later changes to the source guide are not automatically reflected in existing variants