Captio AI

Captio AI vs Yinshu

Captio AI vs Yinshu (音书) for deaf people who read Chinese: phone call captions, Mandarin speech training, Cantonese, offline use, who is talking and prices.

Facts checked on each company's own pages. How we compare

Yinshu

by Guangzhou Voibook Technology Co., Ltd.

iPhone, iPad, Android; Mac and Vision Pro

vs

Captio AI

Our app

iPhone, iPad, Android

The short answer

Pick Yinshu if you want captions on phone calls and video calls, AI scoring to practise your Mandarin pronunciation, or captions shown on a projector in a classroom. Pick Captio AI if you need Cantonese, English or another of 60+ languages with live translation, want to see who is talking around the table, or want to keep conversations as recordings, summaries and exports.

Choose Yinshu if

you want captioned phone calls and video calls, Mandarin pronunciation practice scored by AI, captions on a big screen in a lecture hall, or speech recognition without internet.

Choose Captio AI if

you need Cantonese, English or another of 60+ languages with live translation, want relatives' voices told apart and named on iPhone, or want saved recordings with an AI Summary.

Side by side

Captio AI vs Yinshu, feature by feature

Tap any fact to see the details and the page it comes from.

Captio AI vs Yinshu: features compared, facts checked 28 October 2026
Captions people in the roomCaptio AI
Yes, from the phone's microphone

Speech in the room appears as text while the person is still talking.

Sources: Apple App Store listing, Live Captions (Captio AI)

Yinshu
Yes, speech within 4 metres

Captions speech within about 4 metres, and sound from a TV, computer or speaker, in meetings, training, classes and when you are out.

Sources: Apple App Store listing, Voibook: personal caption services (Guangzhou Voibook Technology (音书科技))

Captions phone callsCaptio AI
No

Made for in-person speech picked up by the microphone, not for captioning phone calls.

Source: Live Captions (Captio AI)

Yinshu
Yes, phone call captions

Voibook lists phone call captions ("see" the other person's voice), and the Android listing describes a phone assistant. The privacy policy says the app can place calls without the phone's dialler. How it works on iPhone and what it costs are not stated.

Sources: Voibook: personal caption services (Guangzhou Voibook Technology (音书科技)), Tencent MyApp (Android) listing (Tencent MyApp (应用宝)), Yinshu privacy policy (Guangzhou Voibook Technology (音书科技))

Captions video callsCaptio AI
No

It is not a video-call captioning service.

Source: Live Captions (Captio AI)

Yinshu
Partly: Its own in-app video calls

Video calls inside Yinshu with family and friends: the other person's speech is shown as text, and your typed text is turned into speech for them. Captioned calls work between users who follow each other, in three modes. Captions for other apps' video calls are not described.

Sources: Apple App Store listing, Voibook: personal caption services (Guangzhou Voibook Technology (音书科技))

Languages for live captionsCaptio AI
Yes: 60+ languages

Captions and translation in 60+ languages, including speech that switches languages mid-sentence.

Sources: Apple App Store listing, Live Captions (Captio AI)

Yinshu
Not stated

Voibook's pages don't list which spoken languages the captions recognise. A July 2023 update added a dialect service without naming the dialects. The app is in Simplified and Traditional Chinese, and its speech training is for Mandarin.

Sources: Apple App Store listing, App Store data (China) (Apple), Voibook: speech training (Guangzhou Voibook Technology (音书科技))

Live translationCaptio AI
Yes, live, two-way mode

Live translation next to the original captions, with a two-way mode where each person reads the other in their own language.

Sources: Apple App Store listing, Live Translator (Captio AI)

Yinshu
Not stated

In Yinshu's own wording, 翻译 ("translation") means turning speech into text. No page describes translating between languages.

Sources: Apple App Store listing, Voibook website (Guangzhou Voibook Technology (音书科技))

Live captions without internetCaptio AI
Partly: Records offline, captions later

Live captions need internet. Without a connection it keeps recording and transcribes automatically when the phone is back online.

Sources: Apple App Store listing, Live Captions (Captio AI)

Yinshu
Yes, offline recognition

The September 2023 release notes added offline speech recognition and an offline lifetime card (离线终身卡). The pages don't say what works offline or what the card costs.

Source: Apple App Store listing

Group conversationsCaptio AI
Partly: One phone: speaker labels, names, direction

One phone captions the whole table and labels each speaker. On iPhone it can name people by their voice, and on iPhone 16 and later a wave shows which side a voice comes from. Shared folders let several people add recordings to one place; live captions are not joined across phones.

Sources: Apple App Store listing, Recognize voices (Captio AI) (Captio AI), Speaker direction (Captio AI) (Captio AI), Live Captions (Captio AI)

Yinshu
Partly: One phone; captions on a big screen

One phone picks up what each person within 4 metres says. For large meetings and lectures, the caption display mode (字幕速记) projects the text onto a big screen or a laptop, readable from 10 metres away. Showing who is talking is not described.

Sources: Apple App Store listing, Voibook: caption services for institutions (Guangzhou Voibook Technology (音书科技)), Yinshu caption display (字幕速记) web page (Guangzhou Voibook Technology (音书科技))

Shows who is talkingCaptio AI
Yes, live and saved; names by voice on iPhone

Separates speakers (Speaker 1, Speaker 2). On iPhone it can learn saved voices and show their names instead.

Sources: Apple App Store listing, Recognize voices (Captio AI) (Captio AI), Live Captions (Captio AI)

Yinshu
Not stated

Yinshu's feature lists on the App Store and Voibook's caption services page don't say the captions show who is talking.

Sources: Apple App Store listing, Voibook: personal caption services (Guangzhou Voibook Technology (音书科技))

Remembers people's voicesCaptio AI
Yes, Recognize Voices (iPhone)

Save someone's voice once (about 20 seconds of talking, or an audio file) and their name and emoji show on every line they say, live and in saved recordings, instead of "Speaker 2". Voiceprints are made on the iPhone and never uploaded. When someone new talks for a while, Captio AI asks who it is. Free plan: your own voice plus one other person; Plus: more people.

Source: Recognize voices (Captio AI) (Captio AI)

Yinshu
Not stated

No page describes learning people's voices or showing their names.

Shows where a voice comes fromCaptio AI
Yes, on iPhone 16 and later

With the iPhone flat on the table, a wave grows at the edge of the captions on the side the voice comes from, in that speaker's colour, while new words appear. It uses the iPhone's spatial microphones (not AirPods or an external mic), works in Live Captions and Live Translator, is calculated on the phone, and is free.

Source: Speaker direction (Captio AI) (Captio AI)

Yinshu
Not stated

No page describes showing where a voice comes from.

Alerts for soundsCaptio AI
Yes, sounds in the captions; alerts vibrate

Recognize Sounds (iPhone and iPad) writes sounds into the captions where they happen, like [doorbell rings], in Live Captions, Live Translator and uploaded files. A doorbell, knocking, a smoke alarm, a siren, a phone ringing or a baby crying makes the phone vibrate, with a notification when the screen is locked during a recording. It works while Captio AI is recording, not as an always-on alarm. Recognized on the phone; free; not on Android yet.

Source: Recognize sounds (Captio AI) (Captio AI)

Yinshu
Not stated

Yinshu's feature lists on the App Store and Voibook's caption services page don't mention alerts for sounds like a doorbell or an alarm.

Sources: Apple App Store listing, Voibook: personal caption services (Guangzhou Voibook Technology (音书科技))

Captions videos playing on the phoneCaptio AI
Partly: Uploaded files only

It does not caption audio playing on the phone, but it can transcribe a saved audio or video file.

Source: Audio Transcription (Captio AI)

Yinshu
Yes: Floating captions over other apps

Floating captions are described for livestreams, Douyin and the news. The listing also covers TV, computer and speaker sound picked up by the microphone. The pages don't say whether floating captions work on iPhone.

Sources: Voibook: personal caption services (Guangzhou Voibook Technology (音书科技)), Tencent MyApp (Android) listing (Tencent MyApp (应用宝)), Apple App Store listing

Sign languageCaptio AI
No

Captio AI works with speech and text only.

Source: Live Captions (Captio AI)

Yinshu
Partly: Text to sign; interpreting services

The release notes mention a text-to-sign-language screen in the app. Voibook also offers online and in-person sign language interpreting and sign language training to institutions and individuals; prices are not stated.

Sources: Apple App Store listing, Voibook: sign language services (Guangzhou Voibook Technology (音书科技))

Saves transcriptsCaptio AI
Yes, with audio, synced

Recordings are saved with their audio in a searchable library and synced to your account.

Sources: Apple App Store listing, Captio AI privacy policy

Yinshu
Not stated

Yinshu's feature lists on the App Store and Voibook's caption services page don't describe saving or reopening transcripts.

Sources: Apple App Store listing, Voibook: personal caption services (Guangzhou Voibook Technology (音书科技))

AI summariesCaptio AI
Yes: Summary, key points, to-dos

Turns transcripts into summaries, key points, notes, to-dos and follow-up messages. Free plan: 3 summaries in total.

Sources: Apple App Store listing, AI Summary (Captio AI)

Yinshu
Not stated

No page describes AI summaries.

Where speech is processedCaptio AI
Yes: Cloud; audio not stored on its servers

Speech is processed by third-party speech recognition after you agree. Audio is not stored on Captio AI's servers; content is never sold or used to train AI models.

Source: Captio AI privacy policy

Yinshu
Partly: Cloud; data stored in China

The privacy policy (February 2023) says personal information collected in China is stored in China. Speech recognition and pronunciation scoring use iFlytek and AISpeech SDKs, and voice data is also used to improve the service. It lists advertising SDKs, and the App Store label lists identifiers and usage data used for tracking. Offline recognition is available.

Sources: Yinshu privacy policy (Guangzhou Voibook Technology (音书科技)), Apple App Store listing

Account neededCaptio AI
Partly: Optional

Sign in with Apple or Google to sync, or skip and use it on one phone.

Source: Captio AI privacy policy

Yinshu
Yes, with a mobile phone number

Creating an account needs a mobile phone number and a username. A WeChat, Weibo, QQ or Apple account can be linked for sign-in.

Source: Yinshu privacy policy (Guangzhou Voibook Technology (音书科技))

Where it's availableCaptio AI
Yes: Worldwide

Available on the App Store and Google Play; prices differ by country.

Sources: Apple App Store listing, Google Play listing

Yinshu
Yes: Made for China; App Store elsewhere too

The app and website are in Chinese, and Voibook's Android download goes to Tencent's MyApp store. The App Store also lists the app outside mainland China, for example in the US store.

Sources: Apple App Store listing, Voibook website (Guangzhou Voibook Technology (音书科技)), Tencent MyApp (Android) listing (Tencent MyApp (应用宝)), App Store data (US) (Apple)

Free planCaptio AI
Yes: 100 free credits a day + 3 summaries

Free every day: 100 free credits a day for live captions or transcription, and 3 AI summaries in total.

Sources: Apple App Store listing, Captio AI for AI assistants (llms.txt)

Yinshu
Partly: Free download; paid top-ups

Free to download, with in-app top-ups. Release notes mention timed translation, extra time for watching videos and a yearly card, but no page says how much is free.

Sources: Apple App Store listing, App Store data (China) (Apple)

Paid plansCaptio AI
Yes: US$14.99/month or US$79.99/year

Captio AI Plus on the US App Store, October 2026. No free trial. Prices differ by country.

Source: Apple App Store listing

Yinshu
Yes: Top-ups from CNY 8 to CNY 98

China App Store in-app purchases, November 2026: top-ups of CNY 8, 15, 38, 58 and 98 (labelled 3 to 98 yuan of credit). The pages don't say what each top-up buys.

Source: Apple App Store listing

Key differences

What actually sets them apart

Does Yinshu caption phone calls and video calls?

Yes. Voibook lists phone call captions and a phone assistant, and Yinshu has its own video calls where the other person's speech appears as text and your typed reply is spoken to them. Captio AI does a different job: it captions the people talking in the room around you, and doesn't caption phone or video calls.

Sources: Voibook: personal caption services (Guangzhou Voibook Technology (音书科技)), Tencent MyApp (Android) listing (Tencent MyApp (应用宝)), Yinshu privacy policy (Guangzhou Voibook Technology (音书科技)), Apple App Store listing, Live Captions (Captio AI)

Can Yinshu help me practise speaking Mandarin?

Yes, and this is where it stands apart. Its speech training scores your pronunciation with AI, in four levels: pinyin, words, sentences and whole texts. Captio AI's four tools, Live Captions, Live Translator, Audio Transcription and AI Summary, are all about reading what other people say.

Sources: Voibook: speech training (Guangzhou Voibook Technology (音书科技)), Apple App Store listing, Captio AI in Chinese

Does Yinshu understand Cantonese or English?

Its pages don't say. A 2023 update added a dialect service without naming the dialects, the app is in Simplified and Traditional Chinese, and its speech training is for Mandarin. Captio AI captions Mandarin, in Simplified or Traditional characters, and Cantonese, among 60+ languages, and Live Translator translates them as people talk.

Sources: Apple App Store listing, App Store data (China) (Apple), Voibook: speech training (Guangzhou Voibook Technology (音书科技)), Voibook website (Guangzhou Voibook Technology (音书科技)), Captio AI in Chinese, Apple App Store listing, Live Captions (Captio AI), Live Translator (Captio AI)

Can I use Yinshu offline on a train or out in the countryside?

Yes. Offline speech recognition arrived in a 2023 update, together with an offline lifetime card; Voibook's pages don't say what the card costs. Captio AI needs internet for live captions; without a signal it keeps recording and transcribes when the phone is back online.

Sources: Apple App Store listing, Apple App Store listing, Live Captions (Captio AI)

Can Yinshu put captions on a projector in a lecture hall?

Yes. Its caption display mode (字幕速记) projects the live text onto a big screen or a laptop, readable from 10 metres away, and the web page signs in with a QR code from the app. Captio AI shows captions on the phone or iPad that is listening; its live captions are not joined across phones.

Sources: Apple App Store listing, Voibook: caption services for institutions (Guangzhou Voibook Technology (音书科技)), Yinshu caption display (字幕速记) web page (Guangzhou Voibook Technology (音书科技)), Apple App Store listing, Recognize voices (Captio AI) (Captio AI), Speaker direction (Captio AI) (Captio AI), Live Captions (Captio AI)

Will Yinshu tell me which relative is speaking at a family dinner?

Its pages don't say it labels speakers. Captio AI marks each new voice from one phone set in the middle of the table. On an iPhone, Recognize Voices writes 妈妈 or 舅舅 in place of "Speaker 2" once you've saved their voices, and on an iPhone 16 or newer Speaker Direction shows the side of the table a voice is coming from.

Sources: Apple App Store listing, Voibook: personal caption services (Guangzhou Voibook Technology (音书科技)), Apple App Store listing, Recognize voices (Captio AI) (Captio AI), Live Captions (Captio AI), Speaker direction (Captio AI) (Captio AI)

Honest take

Where each one wins

Where Yinshu is the better choice

Where Captio AI is the better choice

Try Captio AI free

Which one should you use?

It depends on where you are

Yinshu

Calling a relative or a delivery driver

Yinshu captions phone calls. Captio AI doesn't caption calls; it is for people in the room.

Captions for this situation
Yinshu

A lecture where the captions go on the projector

Yinshu's caption display mode puts the live text on a big screen the whole class can read.

Captions for this situation
Yinshu

A village or a basement with no signal

Yinshu has offline speech recognition. Captio AI records offline and writes the transcript once you're back online.

Captio AI

A Cantonese-speaking grandmother and grandchildren who grew up abroad

Captio AI captions Cantonese and Mandarin, and Live Translator shows a translation next to the original, in 60+ languages.

Captions for this situation
Yinshu

A Douyin livestream with no subtitles

Yinshu's floating captions sit on top of other apps for livestreams and short videos; its pages don't say whether that works on iPhone. Captio AI doesn't caption audio playing on the phone; it transcribes files you upload.

Captions for this situation
Captio AI

A specialist's diagnosis you want to show your family later

Captio AI saves the consultation with its audio and turns it into a summary you can send on as a PDF.

Captions for this situation
How we compare

Facts you can check, not opinions.

From their own pages

Every fact comes from the company's website, help pages, privacy policy or store listing. Tap any fact to see the page it comes from.

Checked 28 October 2026

Each source has the date we opened it. If a company doesn't say something publicly, the table says "Not stated" instead of guessing.

We make Captio AI

So it's described with the same rules as every other app, limits included, and each page says where the other app is the better choice.

Something out of date? hello@captioai.app

FAQ

Frequently asked questions

Is Yinshu free, or do I have to top up?

The download is free. The China App Store lists in-app top-ups from CNY 8 to CNY 98 (November 2026), and release notes mention timed translation, a yearly card and extra time for watching videos, but Voibook's pages don't say how much you can use without paying. Captio AI has no top-ups: you get 100 free credits a day at no cost, and Captio AI Plus lifts the limit for US$14.99 per month or US$79.99 per year (US App Store prices, October 2026).

Is Yinshu on Google Play?

Voibook's own Android download link goes to Tencent's MyApp store, and the Google Play address for its Android package returns no listing. On iPhone it is on the App Store, also outside mainland China. Captio AI is on the App Store and on Google Play.

Does Yinshu caption Cantonese for users in Hong Kong?

Its pages don't say which dialects its 2023 dialect service covers. Captio AI captions Cantonese with Traditional Chinese characters, and Mandarin in Simplified or Traditional characters.

Do I need a Chinese phone number for Yinshu?

You need a mobile phone number to create an account, according to its privacy policy; it doesn't say the number has to be Chinese. WeChat, Weibo, QQ or Apple sign-in can be linked. Captio AI needs no phone number: you can sign in with Apple or Google, or skip signing in and use it on one phone.

Where does Yinshu keep my data?

Its privacy policy says personal information collected in China is stored in China, with speech handled through iFlytek and AISpeech SDKs, and it lists advertising SDKs. Offline recognition is also available. Captio AI also relies on the cloud, and only after you agree; its privacy policy keeps your audio off Captio AI's servers and rules out using your content to train AI models.

Can Yinshu help a deaf child practise Mandarin pronunciation?

Yes. That is one of its two main parts: AI scores the child's pronunciation in pinyin, words, sentences and whole texts. Captio AI is a caption app for reading other people's speech, so for pronunciation practice Yinshu is the one built for it.

Can Yinshu caption a WeChat video call?

Its pages describe captions in Yinshu's own video calls between users who follow each other, and floating captions for livestreams and Douyin, but not WeChat calls. Captio AI doesn't caption phone or video calls at all.

Can Yinshu let me know the doorbell rang while I'm reading captions?

Voibook doesn't describe sound alerts anywhere. In Captio AI, Recognize Sounds on iPhone and iPad catches a knock, a doorbell or a smoke alarm during a recording, puts it into the transcript in brackets, and vibrates the phone for those alerts.

Try Captio AI

Free to start, iPhone and Android

Sources

Every page this comparison uses, with the date we checked it.

Captio AI

Yinshu

Published 2 November 2026. App names and trademarks belong to their owners. This page is not affiliated with or endorsed by the companies it compares.