Google's Gemini app voice input now supports 70+ languages with automatic mixing

At a glance:

• Gemini app's voice input now supports over 70 languages without requiring language setting changes
• Users can mix languages within the same conversation, tested successfully with English and Hindi
• Feature is rolling out now on Android and iOS, with web support arriving within a week

What's new with Gemini's voice input

Google has upgraded the Gemini app's microphone feature to support voice input in more than 70 languages, eliminating the need for users to manually adjust language settings. The update, announced by Josh Woodward, Google's VP for Gemini, on his X account, makes the voice input feature more accessible to multilingual users and non-English speakers worldwide.

The new functionality automatically detects and processes multiple languages within a single conversation, allowing users to seamlessly switch between languages without interruption. This means a user can begin speaking in Hindi, incorporate English words mid-sentence, and Gemini will accurately process the entire utterance without confusion.

While Google hasn't specified which exact languages are included in the 70+ support list, the company has indicated that the most commonly used languages are likely covered. The feature was tested with mixed English and Hindi input, and the results showed that Gemini properly understood the content despite the language switching.

How the update fits into Google's broader AI strategy

This voice input enhancement is part of Google's June Pixel Drop, which delivered numerous new features including updated Gemini models within the Android app. However, the multilingual voice capability extends beyond Pixel devices, benefiting any user of the Gemini app regardless of their smartphone brand.

The improvement aligns with Google's ongoing efforts to make Gemini more accessible to non-English speakers. Recent additions to the platform include the Gemini Omni model and Gemini 3.5 Live Translate, demonstrating the company's commitment to breaking down language barriers in AI interactions.

By removing the need for manual language configuration and enabling natural code-switching, Google is making voice-based AI interaction more intuitive for the majority of the world's population that doesn't primarily speak English.

Availability and what's next

The multilingual voice input feature is currently rolling out to Android and iOS devices, with Google's VP indicating that web support will follow within approximately one week. This staggered release allows Google to monitor performance and gather feedback before expanding to all platforms.

For existing Gemini users, no action is required to access this feature—it should begin working automatically once the update is installed. The seamless integration means users won't need to navigate settings or configure preferences to take advantage of the new capabilities.

Looking ahead, this enhancement positions Gemini competitively against other voice-enabled AI assistants, particularly in markets where multilingual communication is the norm rather than the exception. As AI becomes more integrated into daily communication, features like automatic language detection will become increasingly important for global accessibility.