Setup & Installation
npx skills add https://github.com/veniceai/skills --skill venice-audio-transcription
https://github.com/veniceai/skills/tree/main/skills/venice-audio-transcription
View on GitHubWhat This Skill Does
Transcribes audio files to text through Venice AI's speech-to-text API. It supports five ASR models, from fast English-focused Parakeet to multilingual Whisper, and the endpoint is OpenAI-compatible, so existing SDK code works with just a base URL swap.
You get access to five different transcription models through a single OpenAI-compatible endpoint, so you can swap between speed and accuracy without changing your code.
When to use it
- Transcribing meeting recordings into searchable text notes
- Adding subtitles to short videos with word-level timestamps
- Converting voice memos into draft documents for editing
- Building a podcast search index from episode transcripts
- Switching between fast English-only and multilingual models depending on the input language