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 speakingSamples of new default avatarsWe’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 languagesFull list of language support in Google Vids UIWe’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 modelUser experience of assigning new voices to custom avatarsWith 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 speakingGenerated sample of a directed custom avatarPreviously, 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 startedAdmins: There is no admin control for these features.End users: Visit the Help Center to learn more about using AI avatars in Vids.Rollout paceRapid Release and Scheduled Release domains: Full rollout (1–3 days for feature visibility) starting on June 17, 2026AvailabilityAvailable to all Google Workspace customers and users with personal Google accountsResourcesGoogle Docs Editors Help: Use AI avatars in Google Vids