You’ve seen Otter transcribe a work meeting and it was honestly impressive: speakers labeled, summary at the top, action items pulled out, all before you got back to your desk. Now it’s Sunday night, you’ve got four hours of session audio sitting in your downloads folder, and the thought arrives with the force of the obvious: why wouldn’t this work for D&D?

Short answer: it will work, partially, and the partial part is sneaky. I build a competing tool, so read me with appropriate suspicion, but I’ll make the case the way I’d make it to a friend: here’s exactly what Otter does well at your table, here’s where it quietly hands the job back to you, and here’s how to tell which kind of group you’re in before you’ve burned a month finding out.

What Otter genuinely does well

Otter is a good transcriber. Feed it clear audio and you get clean, timestamped, speaker-separated text at conversation speed, with a summary on top. It’s inexpensive, the editor is pleasant, and for its actual job, meetings, it might be the best-known tool on earth. None of that evaporates because your meeting has a dragon in it. If what you want is a searchable text record of one session, Otter will hand you one, and the first time you watch your four-hour game turn into scrollable text, it feels like the future.

So if your table’s whole ambition is “we’d like transcripts,” you can stop reading and go set it up. Genuinely. A table with transcripts is doing better than ninety percent of tables.

The gap shows up later, and it has three parts.

Gap one: speakers are people, but the game is characters

Otter will correctly figure out that six humans spoke, and with a little training it will even label them by name. Here’s the problem: Mike is three entities. He’s Mike when he asks whose turn it is to get the pizza, he’s Kalden the ranger when he’s in character, and he’s half the NPCs in the scene when the DM is busy. A meeting transcriber has no slot for that. “Mike: I draw my sword” and “Mike: the innkeeper draws HIS sword” look identical to it, because in a meeting they would be the same kind of sentence.

That mapping, speaker to character to who’s-actually-talking-in-the-fiction, is the single most load-bearing piece of context in a session transcript, and no general-purpose tool extracts it, because it only exists at gaming tables. You can reconstruct it while reading, sure. You, personally, every time, forever.

Gap two: fantasy names eat transcription vocabularies alive

Transcription models are trained on how people talk, and people mostly do not say “Szeth-son-son-Vallano” or “the Duchy of Virelosse.” Your proper nouns will come back creatively mangled: Vex becomes “Beck’s,” Zyrathis becomes “zero of this,” and the Duchy of Virelosse becomes a fresh surprise every single week. Otter lets you teach it custom vocabulary, which helps, and which also means you’re maintaining a glossary of your campaign’s proper nouns by hand, updated every time the DM invents a name mid-sentence, which the DM does constantly.

We hit the same wall at Loracle, because every speech model hits it. Our answer was to stop fighting it at the audio layer and fix it at the memory layer: when the campaign’s own record already knows there’s an NPC called Zyrathis, a phonetically similar mangle in the next transcript gets reconciled back to the real name instead of founding a new character. The fix needs a campaign memory to reconcile against. A tool that sees each file once has nowhere to put one.

Gap three: every session is an island

This is the big one, and it’s structural rather than a missing feature. Otter’s unit of the world is the conversation. Your campaign’s unit is the arc: the favor owed in session three that detonates in session eleven, the fisherman who turns out to be the duke, the prophecy whose exact wording suddenly matters eight weeks after it was spoken. Fifteen clean transcripts in a folder answer none of that, because the connections live between the files, and between the files is exactly where a per-conversation tool never looks.

So Wednesday night arrives, your rogue asks whether the smuggler debt is still live, and your options are: search fifteen transcripts for “smuggler” and read every hit in context, or do what tables have always done and argue from memory. I’ve written about what that gap between sessions does to a group, and about why the Craig-plus-elbow-grease pipeline breaks down at the same seam. The pattern repeats with every general tool: the recording layer is solved, the single-transcript layer is solved, and the campaign layer is always, politely, your problem.

The honest answer

Yes, you can use Otter for D&D, and here’s the profile of the table it works for: you want transcripts more than you want answers, someone at your table actually enjoys being the archivist, and your campaign is short or episodic enough that cross-session questions are rare. One-shots, short arcs, a podcast table that edits anyway. For that table, Otter is a fine tool and cheaper than anything purpose-built.

The table it fails is the one running a long campaign, which is most tables that get this far into a post about transcription. For them the archivist job compounds weekly: export, upload, fix the names, re-read old transcripts to answer new questions, maintain the glossary. Every step is small. The sum is a part-time job that lands on the one person who already DMs.

Loracle’s bet is that the campaign layer is the actual product. It sits in your Discord call, you type /record, and after the session the transcript arrives already speaker-labeled, in whatever language your table plays in, with the recap posted to your channel. Then the part Otter structurally can’t do: every session feeds a living record of the campaign, NPCs and debts and prophecies connected across every session they touch, so when the smuggler argument starts, anyone types /chat and gets the answer from the actual scene, with the wording intact.

Try the Otter route first if you’re unsure; it’s the cheapest way to discover which table you are. Just set a reminder for six weeks out that asks one question: “am I still doing the pipeline by hand?” If the answer is yes and you’re still happy, you’ve found your tool. If the answer is yes and you’re tired, the problem was never the transcription.