Try LINE Free

User guide

Choosing Between the Three Products

Differences between AI Translation, AI Speaking and AI Speaking, plus common questions.

Web需登录消耗积分

Choose in one sentence

ProductWho it suitsIn one sentence
AI TranslationSimultaneous interpreting, following a meeting, listening to someone speak a foreign languageListens to the other person, transcribes in real time and translates into a language you can read
AI SpeakingPractising a foreign language and your deliveryListens to you, transcribes sentence by sentence and gives practice feedback
AI SpeakingMock speakings, preparing answersRecords your answers, and in session 2 turns speaking questions into AI reference answers
Need to understand / translate what "someone else" says in a foreign language?
  �?AI Translation

Need to "speak it yourself" and get sentence-by-sentence feedback?
  �?AI Speaking

Need a mock speaking: record your own answers + get reference scripts for questions?
  �?AI Speaking

Comparing the two session areas

AI TranslationAI SpeakingAI Speaking
Session 1 listens tothe other personyouyou (the candidate)
Session 1 main outputSource text + translationTranscript + practice feedbackTranscript + speaking feedback
Session 2 main useText questions / multilingual outputText practice dialogueSpeaking question �?reference answer
Session 2 read-aloud�?�?�?(by default)

AI Translation

AreaWhat you doWhat the system does
Session 1Listen to the other person speaking a foreign languageTranscribes the source and translates it into your reading language
Session 2Ask questions / add context in text (optional)Generates a reply/translation aimed at the other person; can be read aloud

AI Speaking

AreaWhat you doWhat the system does
Session 1You speak into the microphoneTranscribes + gives practice feedback (not interpretation)
Session 2Practise in text (optional)AI replies in text; can be read aloud

The read-aloud button lives in session 2. Session 1 is transcription and feedback and does not play audio automatically.

AI Speaking

AreaWhat you doWhat the system does
Session 1Speak as the candidate in a simulationTranscribes + gives speaking-oriented feedback
Session 2Enter speaking questionsReturns key points for a reference answer; no read-aloud by default

Common misconceptions

MisconceptionWhat actually happens
Speaking = translation plus one extra chatSession 1 in Speaking is already practice feedback, not interpretation
Speaking = translation with different wordingSession 1 in Speaking works like Speaking (you speak �?transcript + feedback); the business settings and session 2 make the difference
Session 1 replies with voice automatically in all three productsRead-aloud is mainly in session 2 (available in Translation and Speaking; off by default in Speaking)
Session 1 is "interpretation" in all three productsOnly Translation listens to the other person and translates

What to fill in under business settings

EntryContent
Settings �?YOYO assistant �?AI Language PartnerAuto-save interval, debug panel (client-side preferences)
Each product page �?business settingsLanguage direction, scene and vocabulary list, speaking toggles, etc. (feeds the AI pipeline)

Examples of scene and vocabulary list (optional):

  • Translation: Broad context: simultaneous interpreting in a business meeting / Vocabulary: agenda, quote, contract
  • Speaking: Broad context: everyday Japanese conversation practice, N3 / Topics: travel, ordering food
  • Speaking: Broad context: Japanese-language speaking for a backend engineer / Role/company: …

Filling in the scene and keywords improves transcription and terminology accuracy; you do not need to pick a "recording environment" separately in settings.

Time interval (seconds): real-time interpretation is segmented automatically by the system; this interval only applies when the fallback recording mode downgrades to chunking.

Common questions

Q: Why are there two session areas?
A: Session 1 handles the main voice flow (listening or speaking); session 2 handles text support (questions, practice dialogue, speaking questions).

Q: Why does only Translation show "source / translation"?
A: Only Translation listens to the other person, so it uses an interpretation-style display. Speaking and Speaking show what you said + AI feedback.

Q: Where is read-aloud?
A: In Translation and Speaking it sits next to the reply in session 2; Speaking does not offer read-aloud by default.

Q: Do I need to fill in the content summary?
A: It is optional. Filling in scene + keywords improves transcription and terminology accuracy and takes effect from the start of the session.

Q: How is this different from YOYO?
A: YOYO is a general assistant; the AI Language Partner is designed for long voice sessions, with chunking, an interpretation/feedback pipeline, bookings and metering.

How to use it (general)

  1. Open the relevant product page
  2. Complete the business settings
  3. Start the conversation �?record / interpret in session 1
  4. Optional: continue in text in session 2
  5. When you finish, you can save it as a voice session

Related links

Last updated: Wed Jul 01

This guide applies to DodoAI Web/App Help Center v1.0.