phuc-nt / my-translator
Real-time speech translation for macOS β open source, no tracking, direct Soniox API
AI Architecture Analysis
This repository is indexed by RepoMind. By analyzing phuc-nt/my-translator in our AI interface, you can instantly generate complete architecture diagrams, visualize control flows, and perform automated security audits across the entire codebase.
Our Agentic Context Augmented Generation (Agentic CAG) engine loads full source files into context on-demand, avoiding the fragmentation of traditional RAG systems. Ask questions about the architecture, dependencies, or specific features to see it in action.
Embed this Badge
Showcase RepoMind's analysis directly in your repository's README.
Repository Overview (README excerpt)
Crawler view**My Translator** is a real-time speech translation desktop app built with Tauri. It captures audio directly from your system or microphone, transcribes it, and displays translations in a minimal overlay β with no intermediary server involved. > π Installation guides: macOS (EN) Β· macOS (VI) Β· Windows (EN) Β· Windows (VI) --- How It Works | Feature | Detail | |---------|--------| | **Latency** | ~2β3s | | **Languages** | 70+ (source) β any target | | **Cost** | ~$0.12/hr (Soniox API) | | **TTS** | Free (Edge TTS, default) | | **Platform** | macOS (ARM + Intel) Β· Windows | --- Features ποΈ TTS Narration (Free) Read translations aloud β **no API key needed** for the default provider: | | Edge TTS β | ElevenLabs | |-|-------------|------------| | **Cost** | Free | Paid | | **Quality** | β β β β β Neural | β β β β β Premium | | **Vietnamese** | β HoaiMy, NamMinh | β Yes | | **Setup** | None | API key required | Speed adjustable from β50% to +100% (default +50%). > π TTS guide: English Β· TiαΊΏng Viα»t π Custom Translation Terms Define how domain-specific words should be translated: Add terms in Settings β Translation β Translation terms. Great for religious, medical, or technical content. π₯οΈ Local Mode (Apple Silicon only) Experimental offline mode using MLX + Whisper + Gemma β runs 100% on-device. JA/EN/ZH/KO β VI/EN. --- Privacy **Your audio never touches our servers β because there are none.** β’ App connects **directly** to APIs you configure β no relay, no middleman β’ **You own your API keys** β stored locally, never transmitted elsewhere β’ **No account, no telemetry, no analytics** β zero tracking β’ Transcripts saved as files locally, per session --- Tech Stack β’ **Tauri 2** β Rust backend + WebView frontend β’ **ScreenCaptureKit** β macOS system audio β’ **WASAPI** β Windows system audio β’ **cpal** β Cross-platform microphone β’ **Soniox** β Real-time STT + translation β’ **Edge TTS** β Free neural TTS (default) β’ **ElevenLabs** β Premium TTS --- Build from Source Requires: Rust (stable), Node.js 18+, macOS 13+ or Windows 10+. --- Star History --- License MIT