Chinese live captions and productivity tool for group settings
For deaf and hard of hearing people.
coming soon
Download for free
Download on theApp Store
Everything you need to follow Chinese group settings
Four tools built for deaf and hard of hearing Chinese speakers.
Follow whoever is speaking
- Captions the active voice at any moment
- Works at dinner tables, parties, and social gatherings
- Place the phone in the centre of the group
- Any accent, any pace
For multilingual groups
- Each person speaks their own language
- You read in yours, in real time
- 60+ languages, no switching
- For international families, mixed-language groups, travel
Transcribe any group conversation
- Record and get the full conversation in writing
- Organised by speaker
- Review who said what after the fact
- Any group size, any language
Key points from any group discussion
- Decisions and takeaways extracted automatically
- Useful for group meetings and community discussions
- Organised into clear sections
- Works on any saved recording
Download for free
Download on theApp StoreEvery situation covered
Designed for the real moments that matter — not just quiet controlled environments.
Chinese New Year reunion dinners where every relative speaks at once — grandparents in regional dialect, parents in Mandarin, siblings mixing in English. Captio AI captions each voice so you follow the whole table, not just the person beside you.
A Sunday dim sum outing where the noise of a full restaurant, clattering trolleys, and overlapping family conversation make lip-reading impossible. Captio AI cuts through the noise and captions whoever is speaking near your phone.
A weekend visit to family where older relatives speak Shanghainese, Hokkien, or Cantonese and the conversation shifts between varieties constantly. Captio AI handles each variety in the same session.
A multilingual household gathering in Singapore, Malaysia, or diaspora communities where Mandarin, Cantonese, and English appear in the same sentence. Captio AI captions each language so code-switching does not break the thread.
A neighbourhood association or community group meeting in Chinese — temple committee, school parents' evening, local residents' group. Multiple contributors, fast speech, no captioning. Captio AI covers it all.
An evening gathering with friends at a hotpot restaurant or someone's home. Fast casual Mandarin at full speed with nobody thinking to slow down. Captio AI follows every exchange.
Most accurate and fastest models
character accuracy
independent benchmark, 2025
real-time captions
first word appears as you speak
Download for free
Download on theApp Store
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.
Why Chinese is hard to understand
Tonal collapse at the dinner table
- Mandarin's four tones distinguish meaning — and collapse in background noise
- Mandarin's four tones distinguish meaning on every syllable: 买 (to buy) and 卖 (to sell) are the same sounds with different tones. In a noisy family gathering — overlapping voices, background TV, air conditioning — tonal contours compress and merge. A deaf person following speech visually cannot recover tonal meaning from lip movement alone: Mandarin lips move identically across all four tones, making the dinner table one of the most acoustically and visually challenging environments for any deaf Mandarin speaker.
Cantonese's nine tones
- Cantonese family gatherings carry nine tonal distinctions into background noise
- For Cantonese-speaking families in Hong Kong, Guangdong, and diaspora communities, the challenge is compounded. Cantonese has nine tones — level, rising, and falling contours in both high and low registers. In a noisy group setting, tonal distinctions compress further, and the visual cues that partially help with Mandarin are even less useful for Cantonese. At a Hong Kong family dinner, a deaf person is navigating nine tones collapsing into background noise simultaneously.
Family dialect switching
- A single family gathering can contain three or four Chinese varieties
- Chinese family gatherings are frequently multilingual. A grandparent speaks Shanghainese or Hokkien; a parent speaks Mandarin; a sibling throws in English. These switches happen mid-sentence without signal, and the phonological shift from Mandarin to a Wu dialect (Shanghainese) or Min dialect (Hokkien, Teochew) is extreme — different consonant inventories, different vowel systems, different tonal patterns. A deaf person tracking Mandarin loses comprehension entirely when a different Chinese variety appears.
Fast casual Mandarin
- Standard Putonghua and casual family Mandarin are not the same language in practice
- Textbook Mandarin is measured, with clear syllable boundaries. Casual family Mandarin compresses syllables, drops endings, and substitutes shorthand throughout: 什么 → 啥, 那么 → 那, 不用 → 甭. In a relaxed family setting, the pace is substantially faster than any formal speech a deaf person may have calibrated to. The gap between what they prepared to follow and what appears at the dinner table is significant.
Mandarin-English mixing
- Urban Chinese gatherings switch languages mid-sentence with no signal
- In mainland China, Hong Kong, Singapore, and the Chinese diaspora, family conversations among educated or younger members routinely mix Mandarin and English: 我们这个 project 的 deadline 是下周。 The switch is unannounced and typically contains the most specific content — names, dates, technical details. A deaf person following one language loses the thread whenever the other appears.
Download for free
Download on theApp Store426 million people. And the family table is where exclusion begins.
China's hearing loss burden is among the largest on earth. A 2021 analysis published in PMC found that hearing loss cases in China grew from 224.4 million in 1990 to 426.5 million in 2019 — nearly doubling in three decades. Projections estimate 561 million people, representing 40.1% of the total population, will have some degree of hearing loss by 2034. A provincial-level study published in the Chinese Medical Journal in 2025 found that the 27.8 million identified with disabling hearing loss — sufficient to significantly impair daily communication — are unevenly distributed across regions, with rural and western provinces carrying the highest burden.
The infrastructure gap is sharpest in informal social settings. No national programme mandates captioning for family life or community gatherings. A CHARLS survey analysis published in PMC (2024) found hearing loss prevalence significant and rising across all Chinese provinces in the 45+ population — the age group that forms the core of the multigenerational family structure central to Chinese social life. The Chinese family gathering — the reunion dinner, the dim sum Sunday, the mid-autumn celebration — is where a deaf or hard of hearing person is expected to participate actively, without any accommodation existing for them.
Captio AI captions Chinese group conversation in real time across Mandarin, Cantonese, and common regional accents — so the New Year reunion dinner, the dim sum table, and the multigenerational family gathering are conversations a deaf or hard of hearing person can follow without sitting at the edge of the room and watching.
Download for free
Download on theApp StoreWhat 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.
Private by default
Download on theApp StoreCaptio AI supports 60+ languages
People love Captio AI
"Family New Year dinners are twelve people — half in Chengdu dialect, half in Mandarin, all talking at once. I used to give up after the first hour. Captio AI on the table means I stay in it the whole evening."
"Cantonese family gatherings are fast and loud with everyone talking over each other. Nine tones into background noise. Captio AI captions each speaker so I'm not just watching the food."
"My family switches between Mandarin, Hokkien, and English in the same sentence. Captio AI follows all of it. Family dinners used to be the hardest part of my week."
"I was starting to avoid family gatherings because the effort of following was too much. Captio AI in the middle of the table changed that. I actually participate now."
"Family New Year dinners are twelve people — half in Chengdu dialect, half in Mandarin, all talking at once. I used to give up after the first hour. Captio AI on the table means I stay in it the whole evening."
"Cantonese family gatherings are fast and loud with everyone talking over each other. Nine tones into background noise. Captio AI captions each speaker so I'm not just watching the food."
"My family switches between Mandarin, Hokkien, and English in the same sentence. Captio AI follows all of it. Family dinners used to be the hardest part of my week."
"I was starting to avoid family gatherings because the effort of following was too much. Captio AI in the middle of the table changed that. I actually participate now."
Download for free
Download on theApp StoreFrequently asked questions
Keep up with the group in Chinese.
Captio AI is free to start
coming soon
Download for free
Download on theApp Store