Captio AI
🦻 Accessibility + 💻 Productivity App

Swedish live captions and productivity tool for group settings

For deaf and hard of hearing people.

Download for free

Download on theApp Store
Captio AI app showing live captions

Download for free

Download on theApp Store
Use Cases

Every situation covered

Designed for the real moments that matter — not just quiet controlled environments.

🍽️Family dinners

A Swedish family dinner — a julafton gathering, a midsommar celebration, or a Sunday family meal — with multiple relatives talking across the table.

🎉Social gatherings and parties

A birthday party or backyard fika gathering where friends and family catch up over coffee and kanelbullar and several conversations run at once.

Friend catch-ups

A catch-up with old friends over husmanskost and beer, with rapid conversation moving across life updates, news, and shared memories.

🌍Multilingual groups

A community gathering at a local Swedish association, parish, or neighbourhood meeting where announcements are made and everyone responds.

👥Community and club meetings

Three generations at a family table — grandparents from a regional dialect (Skånska, Norrland), parents in standard Stockholm Swedish, grandchildren mixing in English.

🏠Shared living situations

A casual evening at a Swedish pub, a friend's home, or a neighbourhood gathering where small groups form and conversations flow.

Performance

Most accurate and fastest models

Swedish
91.8%

word accuracy

independent benchmark, 2025

< 200ms
you speak
captions

real-time captions

first word appears as you speak

Download for free

Download on theApp Store
Captio AI in everyday use
Why Captio AI

Built to keep you in the conversation, not just in the room

Captions whoever is speaking

Captio AI follows the dominant voice at any moment — whoever is loudest in the microphone's direction. In a group conversation, this tracks the active speaker naturally.

Works through background noise

Restaurants, living rooms, parties, outdoor gatherings. Moderate background noise does not prevent accurate captions — Captio AI is built for real environments, not quiet rooms.

Place it in the centre and forget it

Put the phone on the table or in the middle of the group, microphone facing the conversation. No positioning it after every speaker change, no adjusting between voices.

Less effort, less fatigue

The cognitive load of following a group conversation by lip-reading and reconstructing speech is exhausting. Captio AI handles the following so you can direct your energy toward actually being in the conversation.

60+ languages

For multilingual families, mixed-language social groups, or gatherings where people switch between languages mid-conversation. No setup required between language changes.

No setup between conversations

Open the app and place the phone. No configuration per setting, no briefing the group, nothing to manage between conversations. It works for any group, in any situation.

Swedish

Why Swedish is hard to understand

Pitch accent — two tones

  • Two tone patterns distinguish word pairs — neither visible on lips
  • Swedish has a pitch accent system with two distinct contours: accent 1 (single peak) and accent 2 (double peak). Word pairs like *anden* (the duck) vs. *anden* (the spirit), or *tomten* (the plot of land) vs. *tomten* (Santa Claus) differ only in their pitch pattern. At a family dinner table, pitch is entirely invisible on the lips, leaving these pairs completely visually ambiguous.

The sje-sound

  • A sound that varies across regions and produces no consistent lip signal
  • Swedish has a unique phoneme /ɧ/ (the sje-sound, as in *sjö* or *skjul*) that does not exist in other languages and is realized differently across regions — a back-of-throat hushing sound in Stockholm, a more labial sound in southern Sweden. The same word looks different on the lips depending on the speaker's origin, making this common phoneme a constant source of visual ambiguity.

Southern uvular R

  • Skånska uses a different R that sounds and looks different
  • Central and Northern Swedish uses an alveolar trill or tap /r/ produced at the front of the mouth. Southern Swedish (Skånska) uses a uvular /R/ produced at the back of the throat — the same position as French R — with no visible lip or front-mouth movement. At a gathering mixing Malmö and Stockholm relatives, the same consonant appears in entirely different parts of the mouth.

Retroflexion

  • Central and Northern Swedish curl tongue back invisibly
  • Standard Swedish has retroflex consonants in clusters: /rt/ becomes /ʈ/, /rd/ becomes /ɖ/, /rn/ becomes /ɳ/, /rl/ becomes /ɭ/. These are produced with the tongue curled back toward the hard palate — entirely invisible from outside the mouth. Southern Swedish lacks retroflexion, so the same letter sequence looks and sounds different depending on whether the speaker is from Gothenburg or Umeå.

Finland Swedish prosody

  • Finland Swedish has different rhythm and vowel duration
  • Finland Swedish has distinctly different prosody, vowel qualities, and rhythm from Swedish Swedish. At a Nordic gathering that includes Finland-Swedish speakers, the same words appear with different pitch patterns and vowel durations. A deaf person who has trained on mainland Swedish encounters a recognizably different phonological profile.

Download for free

Download on theApp Store
The Challenge

Hearing loss in Sweden: the scale of daily exclusion

Approximately 1.3 million people in Sweden — around 13% of the total population of 10 million — have some degree of hearing loss, making it one of the most prevalent health conditions in the country. A population-based self-report study found that hearing difficulties are significantly associated with lower income and greater dependence on social benefits, with hard-of-hearing adults more likely to receive disability pension and sick leave than the general population. At least 10,000 deaf and hearing-impaired Swedes are under the age of 20, and almost half of all people who would benefit from a hearing aid do not have one.

Sweden has been a leader in deaf rights: Swedish Sign Language was formally recognised as a minority language and Swedish Sign Language interpretation services are available for formal public events and some employment settings. Around 7,400 people are registered users of STS-IS interpretation services, but usage varies considerably — those who are deaf from childhood use interpretation regularly, while others use it more sporadically for formal occasions. Family social events, birthday parties, neighbourhood gatherings, and informal group occasions are not covered by any public or voluntary interpretation service. Research on participation and accessibility for deaf and hard-of-hearing Swedes consistently identifies informal social settings — family dinners, community celebrations, neighbourhood meetings — as the places where exclusion is most acutely felt.

Captio AI captions Swedish conversation in real time on a phone screen — so a deaf family member at a julafton gathering or a midsommar celebration in Stockholm, Gothenburg, Malmö, or Helsinki can follow every story and toast as it is spoken, across whatever Swedish variety or regional accent is at the table.

Download for free

Download on theApp Store
Privacy

What you hear stays with you.

Gone the moment it ends

Captio AI processes your audio in real time and discards it immediately. Nothing is recorded. Nothing is kept.

Not a product

Your conversations are not something Captio AI sells, shares, or monetizes — to anyone, for any reason.

Not used to train anything

What you say in a doctor's appointment or a job interview never ends up in a training dataset. Not ours. Not anyone else's.

100% PRIVATE

Private by default

Download on theApp Store
Reviews

People love Captio AI

"At our julafton dinner my relatives from Skåne and from Norrland sound completely different. Captio AI followed everyone — I finally caught all the family stories."

Maja L. 🇸🇪
maja.l***@gmail.com
Stockholm, moderate bilateral loss since adolescence

"Skånska with its uvular R is very different from standard Swedish and most apps get confused. Captio AI handled my family's speech accurately at a birthday gathering."

Erik H. 🇸🇪
erik.h***@gmail.com
Malmö, severe high-frequency loss

"Finland Swedish prosody is different enough that mainland Swedish speakers often ask us to repeat ourselves. The app followed my family's speech accurately at a family dinner — I stayed in the conversation."

Anna K. 🇫🇮
anna.k***@gmail.com
Helsinki, profound loss, Finland-Swedish speaker

"At neighbourhood gatherings the conversation moves fast and overlaps constantly. Captio AI kept up with the pace — I stopped missing the moments that made everyone laugh."

Johan B. 🇸🇪
johan.b***@gmail.com
Göteborg, moderate loss, wears hearing aids

"At our julafton dinner my relatives from Skåne and from Norrland sound completely different. Captio AI followed everyone — I finally caught all the family stories."

Maja L. 🇸🇪
maja.l***@gmail.com
Stockholm, moderate bilateral loss since adolescence

"Skånska with its uvular R is very different from standard Swedish and most apps get confused. Captio AI handled my family's speech accurately at a birthday gathering."

Erik H. 🇸🇪
erik.h***@gmail.com
Malmö, severe high-frequency loss

"Finland Swedish prosody is different enough that mainland Swedish speakers often ask us to repeat ourselves. The app followed my family's speech accurately at a family dinner — I stayed in the conversation."

Anna K. 🇫🇮
anna.k***@gmail.com
Helsinki, profound loss, Finland-Swedish speaker

"At neighbourhood gatherings the conversation moves fast and overlaps constantly. Captio AI kept up with the pace — I stopped missing the moments that made everyone laugh."

Johan B. 🇸🇪
johan.b***@gmail.com
Göteborg, moderate loss, wears hearing aids

Download for free

Download on theApp Store
FAQ

Frequently asked questions

Keep up with the group in Swedish.

Captio AI is free to start

Download for free

Download on theApp Store