§ Tool 02 of 23 · AI

A translator that listens back.

Nineteen languages, three modes — translate, polish, summarise — and a dedicated word mode that returns phonetics, meanings, examples, and etymology. v2.12 adds OpenAI TTS streaming: PCM audio decoded directly to the speaker, playback in roughly 200 ms, thirteen voices to choose from.

Version
v2.12
May 2026 — current
Languages
19 + auto-detect
Including CJK, Arabic, Hindi
TTS
OpenAI · macOS
13 voices, real-time PCM
Modes
Translate · Polish · Summarise
Word mode auto-engages
DevUtilities AI Translate — three modes, language picker, streaming output, and TTS playback.
Plate ii — AI Translate with the live status indicator and the OpenAI TTS playback affordance.
§ 01Capabilities

Eight pieces, tightly fitted.

i

Three operation modes

Translate renders meaning faithfully. Polish rewrites in the same language for clarity and flow. Summarise condenses long passages into the target language.

ii

Nineteen languages

Auto-detect, English, Chinese (Simplified / Traditional), Japanese, Korean, Spanish, French, German, Russian, Arabic, Hindi, Portuguese, Italian, Dutch, Turkish, Vietnamese, Thai, Indonesian.

iii

Word mode

Drop a single word and the output expands: phonetic notation, primary meanings, sample sentences, etymology — a pocket dictionary inline.

iv

OpenAI TTS streaming

Raw PCM streamed straight to AVAudioPlayerNode. Playback starts in ~200 ms; no sentence splitting; thirteen voices.

v

Native macOS TTS

Fall back to the system voices for any of the nineteen languages — useful offline or when you've blown through your TTS quota.

vi

Real-time streaming

Output streams as the model generates. Live status indicator animates between thinking and done; copy and retry are one click each.

vii

Smart language defaults

Target language is seeded from your system locale on first launch. Override per session; the choice sticks for future runs.

viii

Resizable split view

Source and translation share a split that snaps to a 500 pt cap on input height. Long passages get a scroll, not a clipped box.

§ 02A typical session

Four moves from paste to playback.

Pick a mode & pair

Translate, polish, or summarise. Choose source (or auto-detect) and target.

Mode · pair · model

Paste the text

Single word, sentence, paragraph, or essay. Word mode engages on its own when the input is a single token.

Send ·

Listen if you'd like

Hit the speaker to hear it. OpenAI TTS streams PCM in real time; the macOS engine handles offline playback.

Speaker · ⌘ ⇧ S

Copy or retry

One-click copy on the output. Retry re-runs with the same input if you want a second pass.

Copy · ⌘ C
§ 03Made for these tasks

The work it actually does.

i — Read

Foreign-language docs

Drop a Mandarin RFC or a Japanese commit message; get faithful English back without leaving the window.

ii — Polish

Email and PR rewrites

Polish mode rewrites without translating. Tighten the same paragraph until it reads the way you'd like.

iii — Summarise

Long threads

Summarise into target language: a Slack debate becomes a paragraph in the language you actually publish in.

iv — Learn

Vocabulary, with weight

Word mode returns phonetics, meanings, sentences, etymology. The flashcard you didn't have to make.

v — Listen

Pronunciation practice

OpenAI TTS at native speed. Loop a phrase to learn its prosody, not just its letters.

vi — Write

Marketing copy across markets

Translate first, then polish in the destination language. Two clicks, two passes, one paragraph that reads native.

§ 04Questions, answered

Things people ask before they download.

Which model handles the translation?

The same model picker AI Chat uses. GPT-5, DeepSeek via the Responses API, or any custom OpenAI-compatible model you've added under Settings → AI → Models.

What languages are supported?

Auto-detect plus 19 languages: English, Chinese (Simplified & Traditional), Japanese, Korean, Spanish, French, German, Russian, Arabic, Hindi, Portuguese, Italian, Dutch, Turkish, Vietnamese, Thai, Indonesian.

What's word mode?

When the input is a single word, AI Translate switches to a dictionary-style output: pronunciation (IPA where applicable), primary and secondary meanings, two example sentences, and brief etymology.

How does the OpenAI TTS streaming work?

OpenAITTSService hits /audio/speech with raw PCM streaming. Audio is fed directly into AVAudioPlayerNode as it arrives — playback starts within ~200 ms with no sentence pre-splitting.

Can I use macOS voices instead?

Yes. Settings → AI → Text-to-Speech exposes three modes: Auto (prefer OpenAI when reachable), OpenAI only, or macOS only. The macOS engine works fully offline.

Are translations stored anywhere?

No — except in your local session state, so the panel restores on relaunch. Source text and output are sent only to the model endpoint you configured.

Does Polish mode change languages?

No. Polish mode keeps the language of the input and rewrites for clarity and flow. Use Translate if you want a different language.

§ 05Companion tools

Better with the rest of the shelf.

§ Download

Nineteen languages, three modes, one quiet window.

Download — Mac App Store Changelog