Agent skill · writing content · sundial-org
gemini-stt
Transcribe audio files using Google's Gemini API or Vertex AI
Why this skill is useful
Adds specific commands and integration patterns for using Google's Gemini API that the AI wouldn't reliably generate on its own.
What it needs
Requires python installed locally. Requires google-cloud account access. About 2k tokens when loaded. Last updated 2026-03-07. 639 stars on the source repository.
What this skill does
Gemini Speech-to-Text Skill Transcribe audio files using Google's Gemini API or Vertex AI. Default model is gemini-2.0-flash-lite for fastest transcription. Authentication (choose one) Option 1: Vertex AI with Application Default Credentials (Recommended) The script will automatically detect and use ADC when available. Option 2: Direct Gemini API Key Set GEMINIAPIKEY in environment (e.g., ~/.env or ~/.clawdbot/.env) Requirements Python 3.10+ (no external dependencies) Either GEMINIAPIKEY or gcloud CLI with ADC configured Supported Formats .ogg / .opus (Telegram voice messages) .mp3 .wav .m4a Usage Options Option Description -------- ------------- <audiofile> Path to the audio file (required) --model, -m Gemini model to use (default: gemini-2.0-flash-lite) --vertex, -v Force use of Vertex AI with ADC --project, -p GCP project ID (for Vertex, defaults to gcloud config) --region, -r GCP region (for Vertex, default: us-central1) Supported Models Any Gemini model that supports audio input can be used. Recommended models: Model Notes ------- ------- gemini-2.0-flash-lite Default. Fastest transcription speed. gemini-2.0-flash Fast and cost-effective. gemini-2.5-flash-lite Lightweight 2.5 model. gemini-2.5-flash Balanced speed and quality. gemini-2.5-pro Higher quality, slower. gemini-3-flash-preview Latest flash model. gemini-3-pro-preview Latest pro model, best quality. See Gemini API Models for the latest list. How It Works 1. Reads the audio file and base64 encodes it 2. Auto-detects authentication: If ADC is available (gcloud), uses Vertex AI endpoint Otherwise, uses GEMINIAPIKEY with direct Gemini API 3. Sends to the selected Gemini model with transcription prompt 4. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills sundial-org/gemini-stt