TsubuTalk: AI Speaking Coach
On-device 4axis speech scoring
Free · Designed for iPad. Not verified for macOS.
■ TsubuTalk — AI Speaking Coach, on your iPhone.
TsubuTalk turns the world's most capable AI chatbots (ChatGPT, Gemini, Claude) into your personal speaking coach. Record a short utterance ("tsubuyaki"), get instant 4-axis scoring on device, then hand the transcript off to your favorite AI with a built-in coaching prompt for in-depth feedback on logic, vocabulary, persuasiveness, or grammar.
Your recordings and transcripts stay on your phone — nothing is sent to external servers, ever.
■ Why ChatGPT / Gemini / Claude as your coach?
Whether it's English conversation, TOEFL / IELTS speaking, a presentation, or an interview, you can ask a top-tier AI to "review my logic," "improve my vocabulary," or "make this more persuasive" and get a structured critique in seconds.
TsubuTalk never calls AI APIs directly. You pick a provider (ChatGPT / Gemini / Claude) and the app hands off your transcript via Share Sheet, clipboard, or browser — you paste it into the official app or site yourself. No API key needed.
- 5 built-in coaching prompts: logic / vocabulary / persuasiveness / grammar / custom
- Switch the target provider in settings (ChatGPT default, Gemini beta, Claude beta)
■ Instant on-device 4-axis scoring
Before you hand off to the AI coach, see objective scores instantly on the device:
- Volume (dBFS): average input level vs. a comfortable target range, as a 5-step badge.
- Speech rate: mora/min (Japanese) or syllables/min (English), from the transcript.
- Filler rate: detects fillers ("um", "uh" / "えーと", "あの") and their share of total tokens.
- Pronunciation clarity: a 0-to-1 score from whisper.cpp's recognition confidence.
When any axis falls outside its target range, a short text hint is shown.
■ 330 built-in topic prompts
Beyond a "freestyle" mode, TsubuTalk ships with 330 prompts across 5 locales.
- DAILY: 150 (30 x 5 locales)
- SPEECH (structured / persuasive): 150 (30 x 5 locales)
- ENGLISH (speaking drill): 30 (shared across locales)
A random prompt is offered each time so you never run out of things to say.
■ Progress dashboard
Track scores over 7 / 30 / 90 days with line charts and a 4-axis radar. Streak counter, weekly/monthly counts, and rule-based insights at a glance.
■ Mic calibration
A 5-second calibration personalizes the target dBFS range to your device, so the volume score fits your setup.
■ Privacy — recordings never leave your device
- Recordings, transcripts, scores, and calibration data stay on the device.
- iCloud backup is excluded (NSURLIsExcludedFromBackupKey = true). Data migration is JSON export via Share Sheet (AirDrop / Files) only.
- Crashes are not auto-reported; manual export only.
- The only data leaving the device: AdMob ads, the first-time model download, and text you explicitly send to an external AI chat.
See the in-app privacy policy for full details.
■ Pricing — completely free, ad-supported
The app is completely free. A banner appears on the feedback screen and an interstitial during analysis (Google AdMob, personalized ads disabled). No ad-free plan, no in-app purchase, no subscription.
■ Requirements
- iOS 16 or later
- ~600 MB free storage for the speech-recognition model
- Wi-Fi recommended for the first launch (model download)
■ Supported languages (5 locales)
UI: Japanese / English / Simplified Chinese / Traditional Chinese / Korean
Speech recognition: Japanese / English / Simplified Chinese / Traditional Chinese / Korean / Auto-detect (multilingual whisper model)
■ Who is this for?
- People practicing English conversation, TOEFL / IELTS speaking, presentations, or interviews
- Anyone who wants AI feedback (ChatGPT / Gemini / Claude) on a speech but finds manual transcription tedious
- Users who don't want their voice data sent to external servers — privacy-first by design
- Speakers who want to quantify their speaking with objective metrics (pace, fillers, volume)
■ Contact
Settings > About > Send Feedback, to email the developer directly.
Ratings & Reviews
- This app hasn’t received enough ratings or reviews to display an overview.
Changed:Provider-specific AI hand-off (V2-12): When you send a transcript to an external AI, TsubuTalk now formats it for the destination. For Claude the transcript is wrapped in [transcript] tags, and for Gemini it is fenced with "---", so the AI can more reliably tell your spoken text apart from the instructions, giving steadier feedback. ChatGPT hand-offs are unchanged. Template wording and delivery paths (Share Intent / clipboard / browser) are unchanged.
The developer, Yuji Sugiyama, indicated that the app’s privacy practices may include handling of data as described below. For more information, see the developer’s privacy policy .
Data Not Linked to You
The following data may be collected but it is not linked to your identity:
- Identifiers
- Usage Data
- Diagnostics
Accessibility
The developer has not yet indicated which accessibility features this app supports. Learn More
Information
- Seller
- HARO WORKS
- Size
- 45.2 MB
- Category
- Productivity
- Compatibility
Requires iOS 16.0 or later.
- iPhone
Requires iOS 16.0 or later. - iPad
Requires iPadOS 16.0 or later. - Mac
Requires macOS 13.0 or later and a Mac with Apple M1 chip or later. - Apple Vision
Requires visionOS 1.0 or later.
- iPhone
- Languages
English and 4 more
- English, Japanese, Korean, Simplified Chinese, Traditional Chinese
- Age Rating
4+
- 4+
- Contains
Advertising
- Copyright
- © 2026 HARO Works