Transcribe audio files to text via POST /audio/transcriptions. Covers supported models (Parakeet, Whisper, Wizper, Scribe, xAI STT), accepted containers (wav/flac/m4a/aac/mp4/mp3/ogg/webm), response formats (json/text only), per-model timestamps (word/segment/char), language hints, the 25 MB cap, and per-audio-second pricing. OpenAI-compatible multipart.
Install
npx skills add veniceai/skills --skill venice-audio-transcriptionnpx skills add veniceai/skills --skill venice-audio-transcription -a claude-code -gnpx skills add veniceai/skills --skill venice-audio-transcription -a codex -ggemini skills install https://github.com/veniceai/skills.git --path skills/venice-audio-transcriptiongh skill install veniceai/skills venice-audio-transcriptiongit clone --depth 1 https://github.com/veniceai/skills /tmp/veniceai__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/veniceai__skills/skills/venice-audio-transcription ~/.claude/skills/venice-audio-transcription # Claude Code
cp -R /tmp/veniceai__skills/skills/venice-audio-transcription ~/.agents/skills/venice-audio-transcription # Codex, Cursor, Gemini CLI, Copilot, OpenCode