Skip to content

Introduction

Veronese is an audio-to-text platform for creators. You bring the audio — Veronese turns it into an editable transcript you can polish and publish anywhere.

  1. Ingest — Send audio to Veronese. Upload a file, paste a YouTube URL, forward a podcast feed, send via email, or drop a voice note from Telegram.
  2. Transcribe — Veronese normalizes the audio with FFmpeg and transcribes it using Whisper or Fireworks AI.
  3. Edit — The transcript lands in a rich-text editor. You own every word.
  4. Export — Export as Markdown, plain text, or copy directly to your writing tool of choice.

An episode is the core unit of work in Veronese. Each episode holds one audio recording and its full lifecycle — ingestion state, transcript, and editable content.

Episodes are grouped into series (think: a podcast, a notebook, a project). Every episode must belong to a series. Series keep your work organized and make bulk exports easy.

When Veronese finishes transcribing an episode, it stores two versions:

  • raw_text — the immutable machine output, never overwritten after first generation.
  • content — the user-editable version, seeded from raw_text once. Edit freely.

Transcription is metered in seconds of audio. Your account has a free credit pool (granted at signup) and an optional paid pool (purchased via top-up packages).

ChannelHow it works
Web uploadDrag and drop an audio file in the browser
YouTube / URLPaste a YouTube, X (Twitter), or podcast URL
EmailSend an audio attachment to your personal upload address
TelegramDrop a voice note to the Veronese bot

Create your first episode →