# phuc-nt/my-translator

Real-time speech translation — macOS & Windows, free TTS, no server, your API keys only

Repository: https://github.com/phuc-nt/my-translator
Canonical: https://ross.abutalabs.com/products/my-translator
Language: Python
License: MIT
License Family: permissive
Topics: macos, privacy, real-time, rust, soniox, speech-translation, stt, tauri, tts, windows
Last push: 2026-07-11T08:02:05+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 92, release rhythm 92, longevity 12
- inputs: {"age_days": 173, "days_push": 53, "days_rel": 53, "gap_med": 1, "n_releases_24m": 18}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1275, forks 399 (observed 2026-08-28T04:04:12.957586+00:00)

## What it is
A Tauri-based desktop app that captures system or microphone audio, transcribes it, and shows translations in a minimal real-time overlay, with no intermediary server and using only the user's own API keys. It supports four translation engines (Soniox, OpenAI Realtime, Qwen LiveTranslate Flash, and offline local MLX) plus text-to-speech via Edge, Google, or ElevenLabs.

## Use cases
- translate speech in real time during video calls
- live caption and translate meeting audio on my mac
- transcribe and translate system audio from a webinar
- real-time speech translation on windows
- hear spoken translations of a foreign-language conversation
- offline speech translation without sending audio to a server
- watch translated subtitles of live audio with text-to-speech

## When to choose
- You need ~2-second translated captions of calls or system audio on macOS or Windows
- Privacy matters: audio goes straight from your machine to the chosen engine with your own API keys and no intermediary server
- You want an offline fallback via local MLX models or free TTS via Edge
- You want to swap engines per situation (cheap Soniox, voice-inclusive OpenAI, broad-language Qwen, or fully local)

## When to avoid
- You need Linux or mobile support — builds target macOS and Windows only
- You want batch transcription/translation of recorded files rather than live streaming
- You require a completely keyless free solution — cloud engines need your own API keys, and the offline engine supports only a small set of language pairs (JA/EN/ZH/KO to VI/EN)

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, tts, audio-processing, machine-learning
- domain: speech-processing, developer-tools, privacy
- platform: windows
- tags: speech-translation, real-time-translation, live-captions, tauri-app, overlay-ui, soniox, openai-realtime, qwen-livetranslate, mlx-offline, edge-tts, elevenlabs, byo-api-keys, system-audio-capture, privacy-first, natural-language-processing, macos, desktop, tauri

## Member repositories
- phuc-nt/my-translator (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:12.957586+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:03:03.103789+00:00, confidence not recorded.
  - readme: https://github.com/phuc-nt/my-translator (fetched 2026-08-28T04:04:12.957586+00:00, sha 857db14821b4)
- Data as of 2026-08-30T08:39:29.467469+00:00.