AbdullahHendy/live-translation

Real-time speech-to-text translation over WebSocket. Streams Opus or raw PCM audio from client to server for live transcription and optional translation. Supports CLI and Python API.

56
/ 100
Established

This project helps you translate spoken language into text in real-time. You speak into a microphone, and the system instantly transcribes what you say and translates it into another language, displaying the text as you speak. This is designed for developers who need to integrate live speech-to-text and translation capabilities into their own applications, such as for live captioning or multilingual communication tools.

Available on PyPI.

Use this if you are a developer building an application that requires real-time transcription and translation of live audio streams.

Not ideal if you are looking for a ready-to-use, plug-and-play translation application for end-users, rather than a foundational system to build upon.

real-time communication speech processing live transcription language translation application development
Maintenance 10 / 25
Adoption 5 / 25
Maturity 25 / 25
Community 16 / 25

How are scores calculated?

Stars

13

Forks

7

Language

Python

License

MIT

Last pushed

Mar 11, 2026

Commits (30d)

0

Dependencies

11

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/AbdullahHendy/live-translation"

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