Skip to content

ilkerzg/translator-studio

Repository files navigation

Translator Studio

fal.ai

fal-powered translation suite
Powered by fal.ai


Overview

All-in-one AI translation toolkit: transcription, text translation, speech-to-speech, video dubbing with lip sync, voice cloning, image OCR, and auto subtitles.

Features

Feature Description
Transcribe Convert audio to text with Whisper
Translate Translate text between 50+ languages
Image OCR Extract and translate text from images
Speech-to-Speech Translate spoken audio with voice cloning
Voice Dub Dub video audio without lip sync
Video Dubbing Full video dubbing with lip sync
Auto Subtitle Generate and burn subtitles into video

Architecture

┌─────────────────┐     ┌──────────────────┐     ┌─────────────────┐
│  Audio/Video    │────▶│   Transcribe     │────▶│   Translate     │
│  Input          │     │   (Whisper)      │     │   (LLM)         │
└─────────────────┘     └──────────────────┘     └────────┬────────┘
                                                          │
                        ┌─────────────────────────────────┼─────────────────────────────────┐
                        ▼                                 ▼                                 ▼
               ┌───────────────┐                 ┌───────────────┐                 ┌───────────────┐
               │ Voice Clone   │                 │ TTS           │                 │ Lip Sync      │
               │ (MiniMax)     │                 │ (MiniMax)     │                 │ (Sync)        │
               └───────────────┘                 └───────────────┘                 └───────────────┘

Models

Model Purpose
fal-ai/whisper Speech-to-text transcription
fal-ai/wizper Fast transcription
fal-ai/minimax/speech-2.6-hd Text-to-speech synthesis
fal-ai/minimax/voice-clone Voice cloning
fal-ai/sync-lipsync/v2 Lip sync video generation
fal-ai/nano-banana-pro/edit Image text editing
fal-ai/workflow-utilities/auto-subtitle Auto subtitle generation

Setup

npm install
npm run dev

Enter your fal.ai API key when prompted.

License

MIT

About

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages