Every question, answered

dembrane makes it easier to make sense of big, messy conversations. You bring the room together; participants scan a QR code and their phones turn into dembrane portals. They record every conversation at once, show live results while everyone is still in the room, and deliver an outcome document where every insight traces back to what was actually said. dembrane comes as a self service platform, or as a hosted event where a dembrane event crew member (or one of our founders) runs the session with you.

Participants scan a QR code with their own phone and start talking, in small groups or one on one. dembrane transcribes every conversation live, in more than 150 supported languages and dialects. While the room is still together you see what is coming up across all the tables, and groups can check and refine their own summary. Afterwards you get a report in which every insight links to the quote, and the audio, it came from.

We specialise in empowering huge groups all at once.

Try getting 50 conversations on the record with a standard meeting notetaker - we have tried, it's a huge hassle.

Because we are specialised, we focus on all kinds of useful details: Built in pseudonymisation, Scan to record at scale, monitoring, dynamic dashboards. You name it.

There's other details too: our prompting and methodologies have been refined over thousands of projects and we care about the details, like supporting code switching (when people switch language mid sentence) and making sure the analysis is rooted in the recorded conversations rather than generic online sources.

Any phone newer than an iPhone 8 with a browser can record a conversation: participants scan a QR code and talk. Nothing to install, nothing to hand out.

dembrane can record more than 150 languages and their dialects. We have tested it in English, Strong Irish Dialects, Dutch, Frisian, German, French, Luxembourgish, Basque, Catalan, Welsh, Arabic, Turkish, Polish, Ukrainian, and a room can switch languages mid-sentence (a citizen assembly in Luxembourg runs in four languages at once). Because we refuse to cut corners on transcription, clients tell us it holds up where other tools slip: jargon, local terms, regional accents and mixed-language conversations.

As many as you like: every plan comes with unlimited participants. We do limit the number of concurrent portals: the number of recordings happening at the same time. Workshops are limited to 20 portals at once, and for hosted events, around 100 portals at once is where an event becomes a bigger programme, which gets a custom quote in the intake call.

One of our foundational beliefs is that AI is suspect. Many AI notetakers make a summary of a conversation, and then you might make a summary of a summary, and eventually it's like making a photocopy of a photocopy and the truth degrades. We treat AI as a black box and so should you, but luckily, with big conversations: you have access to the truth right there: the participants!

We have built lots of features that leverage the fact that participants can verify if they feel heard by dembrane's interpretation. Like Verify, where each group gets a first version of dembrane's summary back on the spot and they can refine it by talking on, or typing, until it feels right; that verified record then weighs heavier in the analysis.

At events, live feedback on the big screen is another way that people can share whether they recognise themselves. The final backstop is that insights carry quotes straight from the transcript, with the audio behind them as a source of truth (unless you run in anonymous mode).

You can use dembrane to record and understand any conversation, but it shines at scale! Why have endless meetings when you can host the most impactful moment of the year with all your stakeholders together and completely transform your organisation?

Yes, and you should. Every project has a context field for your goals and the themes you care about; the analysis uses it to frame what it reads. Every view starts from your own research question, and you can hand it a framework to cluster by. There are no default questions, because every session is different. The question participants see on their screen is context too: the framing of the session, visible when they leave the main room. You can also add a list of proper nouns so dembrane can spell them correctly.

With a workaround: You can add text to a project the same way you add a recording: paste a report section, an email or a summary, and it becomes part of the data. We advise keeping a project pure and running the analysis on the conversations first, because documents added up front colour what comes out. Do you need dedicated document upload? Let us know!

For an online session, participants can just scan a QR code and place their phone next to their laptop to record the call which works really well. Audio recorded with another tool can be uploaded to the dashboard afterwards. For dedicated video deliberation we are partnering with Frankly, a platform built by a Harvard and MIT lab. There is no Teams, Google Meet or Zoom integration yet. Do you need one? Let us know!

There are no visuals, so body language is not captured. The analysis runs on what was said, not how it was said: optimism and frustration are usually readable from people's choice of words, and we are experimenting with analysis directly on the audio to detect sarcasm. Because the analysis is never perfect, the result should always go back to participants to check and correct.

Most clients run each session as its own project, create a report per session, then merge projects for one big analysis. Within a project you can chat with specific recordings ("what are the biggest differences between session A and B?"), and tags let you mark tables, locations or themes and filter the analysis by tag.

Nothing is lost. Recording uses very little data, and a phone keeps recording without a connection, then uploads when the connection returns. You can also record locally with any device and upload the audio to the dashboard afterwards if you have no wifi at all. We are considering a "dembrane phone" so you can ask participants to call dembrane instead of scanning a QR code. Interested? Let us know!

Participants mostly just talk. At the end of a conversation they can use the Verify feature to see a first summary and can say what is wrong or missing, which is how we make sure dembrane stays true to what participants want to share. If you want more, you can also configure dembrane to be a brainstorm partner, a blind-spot finder, or a digital socrates to ask difficult questions that take conversations to a deeper level. Afterwards, participants who leave their email can receive a short summary of their own contribution.

Four things. The full transcripts (live). Verified outcomes per conversation (if enabled). An overarching report for the session, written as neutrally as possible from everything that was said and the context you gave, structured around the questions the conversations actually answer. And results to any question you ask to our chat: you can ask where the biggest tensions were, how much depth each theme got, which tables discussed what, and get tables and heatmaps alongside the text.

We have 2 training options: The remote training is €675, takes 2 hours and includes 5 participants. Additional participants at €60 each. Covers responsible use of AI in participatory settings, platform walkthrough, and comprehensive project setup.

The in person training is €2,500, takes 4 hours and includes up to 10 participants. Additional participants at €195 each. This training is a deep dive into methodology, AI risks, hands-on practice with real scenarios, and workspace configuration for your context.

Yes. Every portal is its own recording, so nothing gets mixed. Give each room, track or round its own tag and you can filter the analysis by it afterwards: what did the housing room say, how did round two differ from round one, where did the two locations disagree. Bigger programmes with several sessions on different days usually run each session as its own project and merge them at the end for one overall analysis.

It may be counterintuitive, but when stakes are highest, people are often reassured to see every word carried exactly rather than a note-taker's paraphrase. And participants hold the controls: there is a pause button on every conversation, because the point is not that everything is recorded, but that everything people want to share is. Our longest-running deployment, a people's panel in Northern Ireland, saw more openness, not less.

In the Benelux, a dembrane host (or even one of our founders, let us know) can run the session with you, from intake to report.

In the UK, US, Australia and Germany, we work with partners. Everywhere else, we can provide hands on event support remotely. We train your own team to run the room while dembrane listens live in every language. Not sure what you need? Get in touch and we can figure it out together!

We provide training as part of our EU AI Act risk mitigation strategy. We strongly recommend training your team regardless of where you are based so that they know how to use dembrane effectively and deal with otherwise difficult situations as they might arise.

We offer dedicated trainings to help with that: two hours online for a single facilitator, or an afternoon for a team, and you leave knowing how to design a session, what to ask the data, and how to handle the difficult moments at a table. In the meantime, read how dembrane adds value.

Rolling out a dembrane event usually takes less than a day: you make a free account, we sit together for at least an hour to make sure you can make the most of dembrane, and you are set. We have run events planned five minutes in advance.

This is the thing dembrane was built for. Put one phone on every table: a participant scans the QR code, the phone becomes a portal, and it records that table's conversation for as long as the round lasts. Twenty tables means twenty portals, all transcribing live at the same time, in whatever language each table speaks. While the round is still running you see on the dashboard what is coming up across all the tables, so the plenary can start from what was actually said rather than from three people reporting back. No app, no microphones, no notetaker per table.

Yes, and these are the formats we see most. World Café: the phone stays on the table while people rotate, so every round is recorded and you can ask afterwards how the conversation at a table changed as new people arrived. Open space: whoever opens a session scans a code, and sessions that were never written down anywhere finally end up in the report. Fishbowls, dialogue tables, citizens' assemblies, information evenings with stations: if people are talking in groups, a portal on the table records it. The format stays yours; dembrane just makes sure nothing that was said gets lost.

You can get started for free. Just create an account - We also have 3 paid products: Hosted events, workshops with support, and ongoing use.

In most cases, a hosted event is €1,250 for preparation (intake, event design, workspace setup) and €1,250 per event day, with consultation, event design, dedicated support and server queue priority included. Bigger programmes (on the order of 1000+ people, or more than 100 portals at the same time) get a custom quote in the intake call.

Workshops with support start at €500 per day, that includes a quick-fire training, 1 day of intensive recording with up to 20 portals at once, and access to the platform for a month afterwards (for the analysis). After the first training, it is €350 per workshop day. Workshops are great for between 20 and 50 people.

Ongoing use is unlocked after your first hosted event, workshop, or dedicated training. With ongoing use we scope a custom offer for your team. Ongoing use is ideal for consultancies and participation agencies that run a lot of events and workshops. We customise the offer to fit your budget and needs.

Accommodations can be made if you, for whatever reason, cannot afford dembrane. Just mention scholarships in your intake call.

You can create an account for free. A free account comes with your first hour of transcription, and a single seat already carries a full event: everyone scans the QR code, one person holds the dashboard. Most clients ran one session first: a team day, one table, one round of street interviews. Or bring us along to your next event and get expert care.

We never want money to be the reason you can't listen to your community, but we also never want money to be the reason dembrane goes under. If you need budget assistance, please apply for a scholarship!

Your data is stored encrypted on EU servers. dembrane is ISO 27001 certified and GDPR compliant.

The AI analysis runs on Google Vertex AI under a dedicated agreement with Google, and we use their EU endpoints exclusively, so processing never leaves European infrastructure. We never train models on your data unless you opt in.

Pseudonymisation is a feature you can switch on per project: names and other identifiers are removed before analysis. Your data stays only as long as you keep it: delete a project and it is gone from our servers too.

Our standard data processing agreement is at dembrane.com/legal/dpa, and everything else your data steward will ask about is documented in the trust center.

Yes, you can find our source code on GitHub at github.com/dembrane/echo. Our platform is licensed under the Business Source License (BSL 1.1), which means you can deploy and use it yourself, unless you are using it on behalf of an organisation that makes more than 1 million euros a year, in which case we ask you (kindly) to buy a commercial licence so we can continue to support our development.

We don't do speaker detection because current techniques are not good enough, and giving the analysis models fake data on who is speaking is worse than giving it the verbatim transcript with no such metadata. As a nice side effect that makes the results more egalitarian, it means that what was said counts, not who said it.

dembrane workspaces can be shared with colleagues across different organisations with clear access roles, like a shared document: no bottleneck through one owner. For sensitive projects we provide audit logs. Agencies can make a workspace for each of their clients, with its own billing and separate data ownership controls.

Transcripts can be downloaded from the dashboard at any time, also when a subscription ends. Anything the chat produces can be copied straight into your own document. A direct export of views and reports is being worked on. Audio can be exported unless it was recorded in anonymous mode.

Currently we use Vertex Gemini 3.5 hosted in the EU. Our source code is available on GitHub at github.com/dembrane/echo.

Anyone who has to listen to a lot of people. Lots of municipalities such as Amsterdam, Vienna, Den Bosch and Zaltbommel, Dutch Ministries, the VNG, Provinces, healthcare watchdogs, construction and housing associations, Banks, and lots of NGOs and agencies who run participation projects. Beyond the Netherlands we support a citizen assembly in Luxembourg that runs in four languages at once, and peacebuilding dialogues in Northern Ireland. dembrane started in 2022 in the public domain, and what every client has in common is that dialogue is central to how they work, and something has to be done with what people say.

Any moment where many conversations happen at once and you need to bring them together: assemblies, information evenings, multi-stakeholder sessions, workshops with 20+ people, street interviews, and audio surveys where people talk instead of type. It shines when you want to see where conversations agree, where the biggest tensions sit, and what gets lost in the usual report of "the atmosphere" and a few photos.

We are working on a video right now! In the meantime there is a case study on the peacebuilding work in Northern Ireland, written by People Powered, and this website. Book an intake call or contact us and we can send you something custom that fits your audience.

Eve is co-founder & value lead at dembrane. Her position is about understanding and realising value for clients and dembrane. Additionally she is the main spokesperson, and you have a good chance of seeing her pitch or speak at events.

You can reach out to her when you want better understanding how dembrane could be valuable to your process or event!