Google launches Gemini API CLI: give any coding agent image, video and speech tools
ivan_bezdomny · x · 2026-10-27
Philipp Schmid announced the Gemini API CLI, a stateless command-line tool for calling the Gemini API that you hand to your existing coding agent (Claude Code, Codex, Cursor, Antigravity, OpenClaw) so it can call Gemini without writing curl commands.
- Capabilities: generate images, video, speech and music; analyze PDFs, images, audio, video and YouTube URLs; transcribe recordings to md/json/srt; run Deep Research in the background
- Stateless by design: no memory, no chat mode — your agent owns the context and plan, the CLI just performs API calls
- Self-describing for agents with --help and --dry-run; works with your existing AI Studio API key
More from coding & agent
- CapCut plugin coming to ChatGPT: AI-driven video editing via chat commands — Aiden_Tech_Ai · 2026-10-27
- Map of secure program synthesis: ruby-lean in Lean and the race to formally verify everything — burny_tech · 2026-10-27
- D3-Gym: first auto-constructed verifiable environments for data-driven scientific discovery, shown at EMNLP 2026 — hhsun1 · 2026-10-27
- If Your CLAUDE.md Is Longer Than Your README, Your Agent Gets Harder to Steer — Arindam_1729 · 2026-10-27
- When does checking an AI agent's work cost more than doing it yourself? — Live_Hedgehog8785 · 2026-10-27
- FrontierCS 2 launches on Kaggle with DeepMind: 48 tasks ask agents to beat published papers — lmoroney · 2026-10-27