Enhanced AI avatar features and capabilities in Google Vids

By | June 18, 2026
0 Comment

Enhanced AI avatar features and capabilities in Google Vids

Enhanced AI avatar features and capabilities in Google Vids

Enhanced AI avatar features and capabilities in Google Vids

With the integration of Gemini 3.1 Flash Text-To-Speech (TTS) and the latest capabilities in Veo 3.1, AI avatars in Google Vids have become more realistic and expressive than ever. We’re excited to announce expanded language support, a new collection of avatar defaults, and the ability to direct your custom avatars to take action in any generated video.

Expanded preset avatars with more expressive speaking

Several examples of 3D cartoon avatars
Samples of new default avatars
We’ve expanded avatar options from 23 to 53 default presets, spanning photorealistic, 3D cartoon, and graphic novel styles. This broader gallery includes avatars like Sofia, Jack, Charlie, Finley, and Eleanor, all powered by Gemini Audio to speak with greater degrees of expression, realism, and conversational tones.

Expanded speaker support to 24 languages

List of supported languages
Full list of language support in Google Vids UI
We’ve added support for 16 new languages, including Hindi, Bengali, Marathi, Tamil, Telugu, Arabic, Indonesian, Russian, Dutch, Polish, Thai, Turkish, Vietnamese, Romanian, and Ukrainian. These languages join our existing set—English, Spanish, Portuguese, Japanese, Korean, French, Italian, and German—bringing the total to 24 supported languages for AI avatar and voiceovers.

Create custom avatars with the latest Gemini voice model

UI for creating a custom avatar, including box to add a name
User experience of assigning new voices to custom avatars
With custom avatars in Vids, you can design your avatar using Nano Banana Pro. Starting today, you can choose from 30+ voices powered by Gemini Audio that offer increased expression, language support, and steering control over how they speak.

Direct your custom avatars to take action in addition to speaking

Generated sample of a directed custom avatar
Previously, users could only direct default avatars. Now, you can add custom avatars as an ingredient in generated video clips, unlocking new ways to have your customized spokesperson tell your story. Every generation preserves your custom avatar’s appearance and voice, ensuring your customizations are preserved throughout new generations.
  • Control custom actions: Instruct your avatar to walk, talk, and use objects simply by typing a text prompt describing their actions.
  • Use image references: Upload additional images to direct your avatar in customized locations or with branded logos.

Getting started

Rollout pace

Availability

  • Business: Business Starter, Standard, and Plus
  • Enterprise: Enterprise Starter, Standard, and Plus
  • Education: Education Plus
  • Consumer: All users with personal Google accounts, including Google AI Pro and Ultra
  • Other Editions: Enterprise Essentials, and Enterprise Essentials Plus; Nonprofits; Individual
  • Education Add-ons: Teaching and Learning; Google AI Pro for Education
  • Other Add-ons: AI Expanded Access*
*Users with AI Expanded Access add-on licenses have higher limits on usage of AI avatars in Vids.

Resources

Stop making boring slides because Google Vids just made AI avatars free for everyone - Digital Trends

Google Vids offers highly realistic and expressive AI avatars powered by the Veo 3.1 video and Gemini Audio models. Users can direct default or custom avatars to speak, act, and interact with objects. Expanded language support and emotional controls make creating scalable digital presentations, pitches, and training materials easier than ever. [1, 2, 3]
Core Capabilities & Features from Enhanced AI
  • Directable Custom Actions: Custom avatars can now be told to “walk, talk, and interact with objects” simply by typing a descriptive text prompt. [1]
  • Emotion Steering: Fine-tune the tone and emotional delivery of your digital presenter to perfectly match the intent of your message. [1]
  • Expanded Multilingual Support: Avatars can narrate scripts and lip-sync in 24 supported languages, including Hindi, Bengali, Tamil, Telugu, Spanish, Japanese, and Vietnamese. [1]
  • Slide-to-Video Transformation: Integrate with Google Slides to automatically convert static slide decks into storyboards, complete with an AI script and an avatar to present it. [1]
  • Visual Styling: Choose from 53 default presets, including photorealistic, 2D, and 3D cartoon options for various video tones, or build unique custom avatars using Nano Banana Pro. [1, 2]
  • Unlimited Generation & Consistency: High-fidelity video clips can be generated continuously without previous duration limits, and faces/voices remain entirely consistent across all scenes. [1]

Availability & Usage Limits
  • Free/Personal Accounts: Free users (including personal Google accounts) get a monthly allowance of video generations that can be split between AI avatar creations and standard Veo video clips. [1]
  • Premium/Workspace Users: Google AI Pro, Ultra, Business, and Enterprise subscribers receive elevated limits and can leverage advanced audio and video generation capabilities. [1]
  • Watermarking & Safety: Avatars utilize strict fairness filters to ensure they do not replicate real individuals, and all generated videos include a SynthID watermark for AI verification. [1]

If you want to try these out yourself, let me know:
  • What is the primary goal of your video (sales pitch, training, etc.)?
  • Are you looking to create photorealistic or cartoon-style avatars?
  • Enhanced AI avatar features and capabilities in Google Vids