|

User Guide - RevidAPI Video Translator

Complete guide to using RevidAPI Video Translator

User Guide - RevidAPI Video Translator

Introduction

RevidAPI Video Translator is an AI-powered video translation software that automatically translates videos from one language to another, creates subtitles, and adds AI voice-over with natural-sounding voices.

Video Tutorial

YouTube: RevidAPI Video Translator Tutorial ▶

Watch on YouTube

Installation and Setup

Installation

  1. Download the software from revidapi.com/software
  2. Install the .dmg file (macOS) or .exe file (Windows)
  3. On first launch, you'll be prompted to login or register

Login

  • On first launch, you'll be asked to login or register
  • Use your RevidAPI account to login
  • After successful login, you can use the software

Main Interface

Main Components

Select Video: Button to choose video file(s)
Source Language: Original video language
Target Language: Translation target language
Translation Channel: Translation tool
TTS Channel: Voice synthesis tool
Voice Role: Voice selection
Subtitle Area: Display and edit subtitles

Basic Usage Guide

1 Select Video

  1. Click "Select Video" button
  2. Choose one or multiple video files (supports batch processing)
  3. Selected video path will be displayed in Source Video section
Supported formats: MP4, AVI, MOV, MKV, etc. | Multiple videos supported for batch processing

2 Choose Languages

Source Language:
  • Select original video language
  • Choose "Auto Detect" for automatic detection
  • 30+ languages supported
Target Language:
  • Select translation target
  • Choose "-" for subtitles only (no translation)

3 Choose Speech Recognition (ASR)

Faster-Whisper (Recommended)

Model: large-v3-turbo (Default and Only Available)

  • Fastest with high accuracy
  • 8x faster than large-v3 with similar accuracy
  • Optimized for all video lengths
Advanced Options:
  • Enable CUDA: For NVIDIA GPU acceleration
  • Split Type: Audio splitting mode

4 Choose Translation Tool

Translation Service API Key Required Quality
Google Translate ❌ No Good
Microsoft Translator ❌ No Good
OpenAI ChatGPT ✅ Yes Excellent
Gemini AI ✅ Yes Excellent

5 Choose Text-to-Speech (TTS)

TTS Engine API Key Character Limit Quality
Edge TTS ⭐ Recommended ❌ No ✅ Unlimited High
CapCut TTS ❌ No ✅ Unlimited High
Google TTS (Gemini) ✅ Yes ✅ Unlimited Very High
Choose Voice Role
  • After selecting TTS engine, choose appropriate voice
  • You can choose "No" if you don't want voice-over, only subtitles

6 Advanced Configuration

Option Description Settings
Separate Voice & Background Automatically separate human voice and background music ✅ Check to enable
Result: Keep original background music, only replace voice
Auto Blur Old Subtitles Automatically detect and blur old hardcoded subtitles ✅ Check to enable
Method: OCR or Box detection
Strength: 1-10
Subtitle Type Choose subtitle format None / Soft Subtitle (SRT) / Hard Subtitle (Embedded)
Dubbing Speed Adjust voice speed and synchronization Speed: -50% to +100%
Dubbing Acceler: Auto-match
Slow Video: Auto-sync
Other Options Additional processing options Del inline mute
Align subtitles and audio
Enable CUDA (GPU)

7 Edit Subtitles (Optional)

Action Description
Edit Content Modify subtitle text directly in Subtitle Area
Edit Timing Adjust start and end times for each subtitle
Add/Remove Add new subtitles or remove existing ones
Import SRT Use existing SRT file instead of recognition
Click "Import original language SRT" button
Format SRT (SubRip Subtitle)
Subtitles will be automatically translated after editing

8 Choose Output Directory

Step Action
1 Click "Select Output Directory" button
2 Choose folder to save translated videos
3 Output videos will be saved in this folder

9 Start Processing

Step Action
1 Review all configurations
2 Click "Start" button to begin
3 The software will automatically process:
• Recognize speech → Create original subtitles
• Translate subtitles (if target language selected)
• Generate new voice (if TTS selected)
• Merge video + new audio + subtitles
• Process blur old subtitles (if enabled)

Monitor Progress

Component Description
Progress Bar Shows processing progress for each video
Status Text Shows current status (Recognizing, Translating, TTS, etc.)
Logs Click progress bar to view detailed logs

Processing Steps

Step Description
Prepare Preparation, extract audio
Recognize Speech recognition
Translate Translate subtitles
TTS Generate new voice
Merge Merge video + new audio
Complete Complete

Batch Processing

Feature Description
Select Multiple Videos 1. Click "Select Video"
2. Select multiple files (Cmd/Ctrl + Click)
3. All videos added to queue
Automatic Processing • Process sequentially or in parallel
• Each video has its own progress bar
• Click progress bar to view details

Advanced Features

Feature Description How to Use
1. TTS Standalone
(AI Voice Generator)		 Convert text to audio with AI voices
✅ Unlimited characters
✅ Many languages
✅ Fast speed		 1. Tools → AI Voice Generator
2. Enter text
3. Select language & voice
4. Click Generate
2. Speaker Diarization Automatically distinguish multiple speakers 1. Check "Enable Speaker Diarization"
2. Select max speakers
3. Auto-assign voices
3. Manual Caption Editing Edit captions with timeline 1. After recognition, click "Edit Caption"
2. Edit text & timing
3. Save & continue
4. Custom Subtitle Style Customize Hard Subtitle style 1. Click "Hard Sub Style"
2. Customize: Font, Size, Color, Outline, Position
3. Apply
5. Import Existing SRT Use existing SRT instead of recognition 1. Prepare SRT file
2. Click "Import original language SRT"
3. Select file
4. Skip recognition, only translate & TTS

API Keys Configuration

Service Steps Note
OpenAI API
(ChatGPT)		 1. Setting → OpenAI API
2. Enter API Key from platform.openai.com
3. Choose model
4. Save		 Required for ChatGPT translation
Gemini AI 1. Setting → Gemini AI
2. Enter API Key from makersuite.google.com
3. Save		 Required for Gemini translation & TTS

Note: API keys are stored locally, not sent to server

Common Issues and Solutions

Issue Cause Solution
Cannot recognize speech Audio too quiet or noisy • Increase video volume
• Uses large-v3-turbo (optimized)
• Enable "Remove Noise"
Translation not accurate Using free translation tools • Use ChatGPT or Gemini AI
• Add context in custom prompt
Voice not natural Default TTS voice • Try different voices
• Adjust Dubbing Speed
• Enable "Dubbing Acceler"
Output video error FFmpeg error or incompatible format • Check FFmpeg installation
• Convert to MP4 first
Slow processing No GPU or large model • Uses large-v3-turbo (optimized)
• Enable CUDA if GPU available

Tips and Best Practices

Category Recommendation
Model Information • Default: large-v3-turbo (all videos)
• Optimized for all lengths (short/medium/long)
• 8x faster than large-v3, similar accuracy
Optimize Speed • Uses large-v3-turbo by default
• Enable CUDA if GPU available
• Use Edge TTS (no API, unlimited)
Translation Quality • Use ChatGPT or Gemini AI
• Add custom prompt for context
Natural Voice • Try different voices
• Use "Dubbing Acceler"
• Adjust "Dubbing Speed"
Batch Processing • Process multiple videos at once
• Each video has own progress bar

Support

---

Version: 1.0.0 Last Updated: 2025-01-23