Platform Features

Google's AI platform extends well beyond the Gemini chat interface. This section covers the infrastructure-level capabilities: Gemini-powered translation, cloud-grade speech APIs, text-to-speech models, and the Gemini CLI for terminal-native AI workflows.

In This Section

Translation

Gemini-powered Google Translate — live speech translation, 70+ languages, idiomatic understanding.

Speech-to-Text

Chirp 3 Transcription API and Gemini native audio input — transcription, diarization, multilingual audio.

Text-to-Speech

Chirp 3 HD Voices and Gemini-TTS — 30 voices, 80+ locales, natural language voice control.

Gemini CLI

Open-source terminal AI agent powered by Gemini 2.5 Pro — 1M context, MCP support, autonomous coding.