TheDeathDragon/LiveTranslate

Real-time audio translation overlay for Windows — captures system audio + optional mic input, runs ASR (Whisper/SenseVoice/Qwen3), translates via LLM API, displays subtitles in a transparent overlay.

33
/ 100
Emerging

Implements a modular real-time pipeline with Silero VAD triggering 32ms audio chunks through pluggable ASR backends (faster-whisper, SenseVoice, FunASR Nano, Qwen3-GGUF), then streams translation results character-by-character via OpenAI-compatible APIs with optional JSON schema output and context history. Supports CUDA acceleration, microphone mix-in for hybrid audio capture, and per-model configuration including streaming and thinking-token control—all orchestrated through PyQt6 with a draggable, always-on-top transparent overlay across 14 themes.

No Package No Dependents
Maintenance 13 / 25
Adoption 8 / 25
Maturity 9 / 25
Community 3 / 25

How are scores calculated?

Stars

47

Forks

1

Language

Python

License

MIT

Last pushed

Mar 18, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/TheDeathDragon/LiveTranslate"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.