Guide for implementing Google Gemini API audio capabilities - analyze audio with transcription, summarization, and understanding (up to 9.5 hours), plus generate speech with controllable TTS. Use when processing audio files, creating transcripts, analyzing speech/music/sounds, or generating natural speech from text.
Install
npx skills add alex-tgk/saasquatch --skill gemini-audionpx skills add alex-tgk/saasquatch --skill gemini-audio -a claude-code -gnpx skills add alex-tgk/saasquatch --skill gemini-audio -a codex -ggemini skills install https://github.com/alex-tgk/saasquatch.git --path .claude/skills/gemini-audiogh skill install alex-tgk/saasquatch gemini-audiogit clone --depth 1 https://github.com/alex-tgk/saasquatch /tmp/alex-tgk__saasquatch
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/alex-tgk__saasquatch/.claude/skills/gemini-audio ~/.claude/skills/gemini-audio # Claude Code
cp -R /tmp/alex-tgk__saasquatch/.claude/skills/gemini-audio ~/.agents/skills/gemini-audio # Codex, Cursor, Gemini CLI, Copilot, OpenCode