tencent cloud

Video on Demand

Release Notes and Announcements
Release Notes
Announcements
Product Introduction
Overview
Product Features
Features
Strengths
Scenarios
Solutions
Professional Edition
Introduction to Video On Demand Professional Edition
Quick Start
Console Guide
Development Guide
Purchase Guide
Billing Overview
Billing Modes
Purchase Guide
Viewing Bills
Renewal
Overdue Policy
Refund Policy
Getting Started
Console Guide
Console Overview
Service Overview
Application Management
Media Management
Package Management
License Management
Real-Time Log Analysis
Practical Tutorial
Media Upload
Smart Cold Storage of VOD Media Asset Files
Video Processing
Distribution and Playback
How to Receive Event Notification
How to Migrate Files from Origin Server to VOD
Live Recording
How to Pull from Custom Origin Servers
How to Use EdgeOne to Distribute Content in VOD
Development Guide
Media Upload
Media Processing
Video AI
Event Notification
Video Playback
Media Encryption and Copyright Protection
Broadcast Channel
CAM
Media File Download
Subapplication System
Error Codes
Player SDK
Overview
Basic Concepts
Features
Free Demo
Free Trial License
Purchase Guide
SDK Download
Licenses
Player Guide
Integration (UI Included)
Integration (No UI)
Advanced Features
API Documentation
Player Adapter
Player SDK Policy
Server APIs
History
Introduction
API Category
Other APIs
Media Processing APIs
Task Management APIs
Media Upload APIs
Media Management APIs
Event Notification Relevant API
Media Categorization APIs
Domain Name Management APIs
Distribution APIs
AI-based Sample Management APIs
Region Management APIs
Data Statistics APIs
Carousel-Related APIs
Just In Time Transcode APIs
No longer recommended APIs
Making API Requests
AI-based image processing APIs
Parameter Template APIs
Task Flow APIs
Data Types
Error Codes
Video on Demand API 2024-07-18
FAQs
Mobile Playback
Fees
Video Upload
Video Publishing
Video Playback
Web Playback
Full Screen Playback
Statistics
Access Management
Cold Storage
Agreements
Service Level Agreement
VOD Policy
Privacy Policy
Data Processing And Security Agreement
Contact Us
Glossary

Smart Subtitles

PDF
Focus Mode
Font Size
Last updated: 2024-11-04 10:46:28

Overview

With VOD II capabilities, you can automatically generate multilingual subtitle files for video content. This is suitable for short dramas aimed at international markets, multilingual online education courses, and organizing multinational audio and video conference minutes.
The smart subtitling feature includes the Full Speech Recognition and Voice Translation capabilities. The former uses advanced ASR algorithms combined with massive training data, providing high accuracy even in conditions with ambient noise and background sounds. The latter leverages the advantages of Neural Machine Translation (NMT) and Statistical Machine Translation (SMT), learning translation knowledge from large multilingual corpora to achieve high-accuracy translations from the source language to target languages. Currently, it supports translation for dozens of languages, including Chinese, English, Japanese, Korean, French, Spanish, Italian, German, Turkish, Russian, Portuguese, Vietnamese, Indonesian, Thai, Malay, Arabic, and Hindi.

Suitable Scenarios

Voice Translation Scenarios

Scenario
Description
Short Dramas Going Global
For short dramas targeting international audiences, smart subtitling supports efficient output of multilingual translated subtitles, increasing the efficiency of generating global versions of short dramas.
Movie/TV series
When movies and TV series are released in different countries or regions, adding local language subtitles helps in their dissemination. Smart Translation Subtitles can automatically generate subtitles in the target country's or region's language, which greatly improves efficiency compared to manual subtitling.
Multinational Audio/Video Meetings
For key multinational meetings, recordings can have participants' native language subtitles automatically generated to help with organizing meeting minutes and viewing.
Multilingual Recorded Courses Learning
When online education courses are released in different countries or regions, smart translation subtitles can automatically generate local language subtitles, making it easier to understand and learn.

Speech Full Text Recognition Scenarios

Scenario
Description
Online classes
Smart subtitling can automatically generate subtitles for online course recordings to make it easier for viewers to learn the content of the course.
Social media platforms
General users can add subtitles to their vlogs and share them with others.
Movie/TV series
Old videos are often not subtitled, which makes it difficult for some viewers to enjoy them. The smart subtitling feature can automatically generate subtitles for such videos, which is much more efficient than manual subtitling.
Audio/Video meetings
Subtitles can be automatically generated for recordings of important meetings to facilitate minutes generation. Subtitles also make it easier for viewers to navigate meeting recordings.
Speech quality control
Subtitles can be generated for call recordings to help call centers quickly evaluate the quality of customer service, improving the efficiency of speech quality assurance.

How to Use

Method 1: Launching tasks via the console

You can launch Speech Recognition tasks via the VOD console. Use templates to specify the recognition items as either "Speech Full Text Recognition" or "Voice Translation" for the tasks. Once the task is complete, refresh the subtitle list to view the recognized or translated subtitle files. For detailed instructions, please refer to How to Add Subtitles to Videos.

Method 2: Launching tasks via API

Launching Voice Translation Tasks

Intelligent subtitles are implemented through the audio and video CR feature of speech translation. Specific usage steps:
1. Create an audio and video CR template, enable the speech translation configuration option (AsrTranslateConfigure) switch (Switch), set the media source language (SrcLanguage) and the translation target language (DstLanguage), specify the subtitle file format (SubtitleFormats) and set the subtitle name (SubtitleName):
{
"AsrTranslateConfigure": {
"Switch": "ON",
"SrcLanguage": "zh",
"DstLanguage": "en",
"SubtitleFormats": ["vtt", "srt"],
"SubtitleName": "test"
}
}
Get the template ID from the response.
2. With the template ID obtained in step 1, initiate a smart subtitling task as instructed in Task Initiation.
3. Get the task result as instructed in Getting Result.

Initiate a full speech recognition task

You can implement subtitles through the Video Content Recognition full speech recognition feature as follows:
1. Create an audio/video content recognition template, enable the full speech recognition configuration item (AsrFullTextConfigure) switch (Switch), set the media source language (SrcLanguage), specify the format for the generated subtitle file (SubtitleFormats) and set the subtitle name (SubtitleName):
{
"AsrFullTextConfigure": {
"Switch": "ON",
"SrcLanguage": "zh",
"SubtitleFormats": ["vtt", "srt"],
"SubtitleName": "test"
}
}
Get the template ID from the response.
2. With the template ID obtained in step 1, initiate a smart subtitling task as instructed in Initiating a Task.
3. Get the task result as instructed in Getting the Result.

Help and Support

Was this page helpful?

Help us improve! Rate your documentation experience in 5 mins.

Feedback