Recording your D&D game with Craig, the Discord bot that gives you one file per player

Have the consent conversation first

Do this before the setup, not after, because it is the part that actually matters and the part most guides skip. Craig's own documentation puts it bluntly: it is both immoral and illegal to record anyone without their permission. Recording law varies by jurisdiction and your table may span several of them.

The conversation is short and worth having out loud rather than in a text channel. Say what you are recording, why, where the audio goes, and how long you keep it. In practice most tables are fine with "I want to write better recaps and I keep forgetting NPC names." What people object to is finding out afterwards.

Craig is built to make covert recording hard, which is a point in its favour. It renames itself to add "[RECORDING]" to its nickname while it is running, and it will not record at all if it cannot change its own nickname. If someone joins late, the bot in the member list is the disclosure.

• Ask before the first session you record, not mid-session
• Say who can access the audio and for how long
• Agree what happens to out-of-character conversation in the recording
• Give anyone who is uncomfortable a real way to say no

Setting it up

If you have not settled on Discord recording generally yet, the broader Discord recording guide covers the alternatives and when Craig is the wrong choice. This page assumes you have picked it.

Invite Craig to your server from craig.chat. When you invite it, make sure it can send messages, join voice channels, change its own nickname and send you a direct message — the nickname permission is not optional, because that is how it signals recording, and it refuses to run without it.

To start a recording you need the Manage Server permission, or an access role your admin has granted with /server-settings. That catches people out on servers where the DM is not the owner.

1. Join the voice channel your game runs in
2. Type /join — optionally naming a channel, as in /join channel: Recording
3. Check the bot's nickname now reads [RECORDING]
4. Play your session
5. Type /stop when you are done

It is /stop, not /leave

Worth stating plainly because the wrong command is in a lot of older write-ups: the current command set is all slash commands, and there is no /leave. You start with /join and you end with /stop.

Two others earn their place. /note drops a timestamped marker during the session, which is the cheapest possible way to find "the bit where they killed the duke" in a four-hour file later. And /recordings lists your last five, which is how you get your download link back if your DMs are closed.

One genuinely useful quirk: Craig sends you the download link at the *start* of the recording, not the end, by direct message — and you can download while it is still recording. If Discord crashes mid-session, the link you already have still works.

The free limits, and what happens when you hit them

On the free tier Craig records up to 6 hours in one recording and keeps the audio for 7 days before it expires. Both numbers matter for a normal game: a four-hour session is comfortably inside the limit, but a long one-shot or a session that runs over is not, and a week is easy to lose to a busy weekend.

When the time limit is reached Craig stops the recording and tells you it has hit the maximum, rather than silently truncating the file. That is the good version of that behaviour, but it still ends your recording mid-session.

The practical advice is to download the audio the same night. The link arrives at the start, so this costs you nothing, and it removes the 7-day clock from your life entirely. Patron tiers extend both limits, and any patron can link Google Drive, OneDrive or Dropbox for automatic backup.

Multi-track is what you get; single-track is the paid one

This is the part most explanations get backwards, so it is worth being precise. Craig records every speaker to their own file by default — that is the whole point of it, not an option you enable. What you download is a ZIP containing one audio file per person.

A single-track mix, where everyone is combined into one file, is the *paid* feature: the mixed-down options are gated behind Craig's $4 patron tier. So on the free tier the choice is not "multi-track or single-track" — it is multi-track, and if you want one combined file you either pay or mix it yourself.

Multi-track is genuinely better for a game anyway. You can level the quiet player, cut the person whose dog barked for ten minutes, and drop out-of-character sidebars without touching anyone else's audio.

Which export format to pick

Craig offers more formats than anyone needs, so here is the short version. If you want to edit the session, download the Audacity project — it is FLAC inside an .aup zip and it opens with every track already laid out, which saves you assembling them by hand. If you want files to keep or feed to something else, take FLAC: it is lossless and Craig's own primer recommends it when your software supports it and your connection can handle the size.

Take AAC if the download size matters or you are on a slow connection. It is lossy but it is the most widely supported lossy format, and for spoken word the difference is not what will limit your transcript quality.

Do not reach for WAV out of habit. Craig only offers reduced-quality WAV directly — the listed options are ADPCM and 8-bit — so the familiar name is the worse file here. FLAC is the lossless one.

A correction worth making because it circulates: people often describe Craig's output as per-speaker .ogg files. Ogg formats are available — Ogg FLAC, Opus and Ogg Vorbis are all in the alternate-formats list — but what you get is whichever format you chose on the download page, delivered as a ZIP. Pick FLAC and you get FLAC.

• Editing the session → Audacity project (FLAC in an .aup zip)
• Archiving, or feeding to transcription → FLAC
• Slow connection or storage-constrained → AAC
• Avoid the WAV options — Craig's are reduced quality

Opening the files

The download is a ZIP. Every modern desktop operating system opens one without extra software; on a phone you will need a ZIP extractor app, which is a good reason to do this on a computer.

Inside, one audio file per speaker, named for the person. If you took the Audacity project instead, open the .aup and the tracks are already stacked and aligned.

Run Giarc as well, not instead

Giarc is a backup clone of Craig, hosted in a different country. The common misunderstanding is that it is an alternative to pick between; it is not. You invite both bots to your server, bring both into the voice channel, and run /join on each. You end up with two independent recordings and two download links.

For a session you cannot repeat — a finale, a character death, a one-shot with a guest — that redundancy is cheap insurance against one bot dropping out. It is still a current, documented part of the product rather than a legacy curiosity.

The other capture path, and self-hosting

Craig also has a browser-based webapp, enabled with /webapp on, where participants join through a link instead of relying on Discord's audio. It captures Opus at 128kbit — better than Discord's own — and patrons can record lossless FLAC through it. Worth knowing if Discord audio quality is your bottleneck.

Craig is open source under the ISC licence and actively developed. Self-hosting is officially documented but Linux-only and genuinely involved — PostgreSQL, Redis, Node, PM2, Docker and a stack of audio tools — so it is a project rather than an afternoon.

Now you have six hours of audio and no notes

This is the part nobody warns you about. Recording is solved; the recording is not the thing you wanted. What you wanted was to know what happened, and a ZIP of audio files is arguably worse than notes because it feels like you have the session when you have only deferred the work.

Craig produces audio and nothing else — no transcription, no summarising. So the next decision is what turns it into text.

Running Whisper yourself is free and works well on plain speech. The two things it does badly are the two things a D&D session is made of: it mangles invented proper nouns, because it has never seen your NPC names and will spell them differently every session, and it does not label who is speaking. The fantasy-noun half of that is what campaign-aware transcription exists to fix. The speaker half is where Craig's multi-track output actually helps — transcribe each speaker's file separately and you have attribution Whisper could not give you, at the cost of doing it several times and interleaving the results by timestamp.

Otter and similar meeting tools handle speakers well and handle fantasy names worse, and are priced for meetings rather than for four-hour weekly sessions.