Intelligent transcription with Gemini 3.5 Transcribe

Google has introduced Gemini 3.5 Transcribe, a speech-to-text model that converts spoken audio into written text while handling background noise, specialized vocabulary, and multiple languages automatically. Unlike traditional speech recognition, the model cleans up natural speech patterns by removing filler words and self-corrections, and can understand context to improve accuracy. The model is available to developers through APIs for both real-time voice applications and recorded audio processing, and is being integrated into Google products including the Gemini app, Android, and Chrome. According to the company's measurements, the model achieves lower error rates than its predecessor and performs better across noisy environments and over 85 languages.