Google Launches Gemini 3.5 Transcribe Voice-to-Text Model

Google has launched the Gemini 3.5 Transcribe voice-to-text model, designed to optimize the voice input experience. This model can filter out filler words in real-time, automatically correct verbal mistakes, and supports audio from conversations in 85 languages with up to three speakers. It is currently enabled in the 'Rambler' feature of the Gboard keyboard on Pixel 11, with plans to expand to more services in the future. Compared to its predecessor, Chirp 3, the transcription speed has improved by approximately 70%, and the real-time error rate has dropped to 5.5%. The model supports a customizable vocabulary, but due to its semantic understanding and text refinement capabilities, it may alter the original wording, making it unsuitable for scenarios that require strict adherence to the original speech.

This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.