Gemini can now clone your voice and perform scripts like an actor

Google has rolled out a significant upgrade for its Gemini artificial intelligence platform, introducing advanced features that let users clone their voices and execute scripts with dramatic flair akin to a professional actor.

The update expands the system's capabilities by adding over 2,000 voices alongside much finer delivery controls. Instead of monotonous reading, the AI can now modulate tone and pacing to match the required emotional context of a script.

Furthermore, the upgrade introduces support for two-speaker scenes, allowing for more complex and natural-sounding dialogues between multiple characters within a single generated audio stream.

For tech creators and developers in emerging markets, these advanced audio synthesis tools offer immense potential for localization, podcast production, and independent media projects where high-end voice acting resources might be limited.

As voice cloning technology continues to evolve rapidly, tools like Gemini are setting a new standard for how artificial intelligence interacts with human media and entertainment.