venice-transcribe
by sabrinaaquino
CLI UtilitiesBrief
Transcribe audio to text using Venice AI's Whisper-based speech recognition.
Description
What This Skill Does
Complete toolkit for the Venice AI API, covering image generation, video, audio transcription, text-to-speech, embeddings, and account admin. All inference runs with zero data retention and no training on your data.
Venice AI processes requests without logging or training on your data, making it a privacy-preserving alternative to mainstream inference APIs.
When to Use It
- Transcribing recorded interviews or podcasts to text
- Generating images from text prompts for mockups or content
- Converting written scripts to speech in multiple voices
- Removing backgrounds from product or portrait photos
- Building vector embeddings for RAG pipelines
Example Workflow
User asks: Transcribe this recorded interview in Spanish
- 1
Accepts the audio file path from the user
- 2
Runs transcribe.py with the --file and --language es flags against the Venice API
- 3
Receives JSON response with transcribed text and optional timestamps
- 4
Saves output to a text file with --output
Full text transcript of the interview in Spanish, saved to the specified file
Requirements
- VENICE_API_KEY environment variable (obtain from venice.ai Settings → API Keys)
Installation
clawhub install sabrinaaquino/venice-transcribeRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.