A Mac app for language learners

Speak first.
Polish it later.

Turn the foreign language you speak into subtitles, a study blog post and word-highlighted subtitle videos. Even if you stumble, SpeakLog transcribes it, puts what you said next to a more natural version, and helps you fix it one sentence at a time.

Transcribes, renders and exports on your Mac · Japanese, English, Chinese, Korean and more

Video · Preview
昨日きのう、友達ともだちと新あたらしいカフェに行いきました

Yesterday I went to a new café with a friend.

Illustrative subtitle example, not an app screenshot Noun Verb Adjective Particle Now reading
Current release
0.3.0
Requirements
Apple silicon · macOS 26+
On your Mac
Transcription, rendering, export
Optional AI
Review, blogs, analysis
Why SpeakLog

What learners lack most is speaking.

Many people wait until they're ready and can say it right, so they never say it at all. Those who do speak are left with nothing afterwards: no idea what went wrong, and nothing to show for it.

01

Just talk, no script

Record a quick take, or import a vlog or talking-head video you've already shot. No script, no waiting until you're "ready".

02

Compare the original and revision

Raw recognition is retained separately from reviewed and natural wording. Compare the source recording with your practice record to revisit your expression and later edits.

03

Polished, then published

Your original plus the improved version is a genuine study record. Export it as subtitles, a blog post or a video for the platforms you already use.

How it works

Four steps from a recording to a finished piece.

  1. Speak

    Drag in a voice memo, vlog or talking-head video, or hit record in the app. Imported files are referenced at their existing location.

  2. Transcribe

    On-device speech recognition with per-word timestamps and confidence, split into sentences at pauses. Speed depends on hardware, language and media.

  3. Review

    AI flags misheard words and unnatural phrasing, with reasons. Accept, skip or edit each sentence from the keyboard.

  4. Publish

    Export subtitles, a study blog post and a subtitle video — in any order, or just the one you need.

Two subtitle layers

What you said, and how a native speaker would say it — side by side.

  • As said only fixes what the machine misheard. Your grammar mistakes stay, so it reflects your real level.
  • Natural rewrites awkward phrasing the way a native speaker would, with a category and reason for every change.
  • Explanations are written in your own language, and the depth adapts to your level (CEFR, JLPT, HSK, TOPIK…).
  • Read the improved script from a teleprompter and re-record; subtitles align automatically.
As said
Natural
ParticleA destination takes に or へ; を marks a place you pass through or leave.
As said
Natural
ConjugationThe past of an i-adjective is 〜かった, not 〜でした. Use すごく to modify an adjective.
What you make

Speak once, get three things ready to post.

SpeakLog only exports — there's no SpeakLog social network. Where your work goes is up to you.

Subtitles

Timed, reviewed subtitles. Keep your original words or use the improved version, and add a translation for bilingual captions.

  • SRT / VTT / ASS
  • ASS keeps part-of-speech colors and keywords
  • Or burn them straight into the video

CapCut · Aegisub · Final Cut · YouTube

Study blog

A study note: your text first, then "what I said → more natural" pairs, grammar points and a vocabulary list. Templates keep a series consistent.

  • Markdown / HTML
  • Rich text that pastes into note and Medium
  • Split into a numbered X thread

note · Medium · X · Obsidian · static blogs

Subtitle video

Karaoke-style word highlighting, part-of-speech colors, readings and translations. Preview and export share one renderer, so what you see is what you get.

  • Original video, subtitles only, or a different video
  • 16:9 · 9:16 · 1:1
  • Trimming, pause tightening, face blurring

YouTube · Instagram · TikTok · Bilibili

More features

Details built for speaking and learning.

Practice language per project

English, Japanese, Chinese, Korean, French, Spanish, German… set per project.

Readings per language

Furigana for Japanese, pinyin for Chinese, romanization for Korean and Russian — or just part-of-speech colors.

Topic prompts

Nothing to say? Draw a topic, or let AI suggest a batch matched to your level.

Live captions while recording

Hit record to start; stop and it becomes a project.

AI assistant

Tell it in one sentence how to fix subtitles, rewrite the blog or organize notes. Every change can be undone.

Face blurring

Detects faces on your Mac and lets you pick who to blur. You, the person filming, stay unblurred by default.

Multi-media projects

Import several videos and photos at once; AI writes an overview, rates each clip and analyzes content and visuals.

External agents

A built-in MCP server lets Claude Code or Codex read and edit projects and export videos.

Practice lesson videos

Have AI write a lesson in the SpeakLog format; it builds Q&A cards, shadowing drills or vertical video diaries with captions. Record each line and export.

Hear a model reading first

Play a model reading of any sentence before you speak — macOS voices, VOICEVOX, AivisSpeech or Azure. Unrecorded lines can use the voice for now.

Japanese pitch marks

Japanese sentences show pitch accent, phrase breaks and pauses, so you can read closer to natural speech.

Speaking improvement

AI groups corrections across recordings into recurring issues, with causes, fixes, practice sentences and trends.

Privacy, on your Mac

Local processing, with AI data flow you can check.

Transcription, video rendering, face blurring and export run on the Mac. Cloud review, blogs and assistant features send the text and context they need; visual analysis passes sampled frames or photos to Claude Code or Codex. Selecting an on-device model does not make every feature offline. Read about data flow and AI costs

Claude Code CLIUses your signed-in claude; choose Sonnet, Opus or Haiku
Codex CLIUses your signed-in codex
Anthropic APIYour API key is stored in the macOS Keychain
Apple on-device text modelRequires available Apple Intelligence; visual analysis uses a CLI
FAQ

Questions you might have

Which languages does SpeakLog support?

Practice languages are set per project, including English, Japanese, Chinese, Korean, French, Spanish and German. Transcription depends on macOS speech support and may need a model download on first use. Explanation and translation languages are set separately.

Are my recordings and videos uploaded?

Transcription, rendering, face blurring and export run locally. Cloud AI sends the text and context each feature needs. Visual analysis passes sampled frames or photos to Claude Code or Codex; it still uses Codex when the global provider is the on-device model. Check automatic review and provider settings before using private content.

Will the AI overwrite what I actually said?

Transcription and natural wording are separate layers, and review lets you accept, skip or edit suggestions. The AI assistant and external agents can edit subtitles and other project content, so separate layers do not make every field immutable. Keep the original media and review important changes.

What do I need to run it?

The current 0.3.0 package requires an Apple silicon Mac (M-series chip) with macOS 26 or later. Intel Macs are not supported by this package. The on-device text AI also requires available Apple Intelligence.

Which formats can I export?

Export SRT, VTT or ASS subtitles; save Markdown or HTML blogs, copy rich text to note or Medium, or split text into an X thread. Video exports are MP4 in 16:9, 9:16 or 1:1. You upload or publish the results yourself.

SpeakLog app icon

Say something today.

It doesn't have to be good — speak first, polish it later.

Download for Mac

Current version 0.3.0 · Apple silicon (M-series) · macOS 26+ · Apple-notarized installer · DMG and previous versions