Overview
Menu
Docs Overview/
Tencent MPS Documentation/
Smart Subtitle Template/

Smart Subtitle Template

Last updated: 2025-11-19 14:53:35Download PDF

Overview

The smart subtitle feature can perform Automatic Speech Recognition (ASR) on the voice information in on-demand video files or live streams, convert it into subtitles, and translate it into multiple languages. It is suitable for scenarios such as live subtitles for streaming and video translation for overseas distribution. You can create custom smart subtitle templates and preset different process parameters for different use cases, to facilitate subsequent reuse.




Prerequisites

1. You have signed up for a Tencent Cloud account.
2. You have activated Media Processing Service (MPS) and logged in to the MPS Console.

Template Configuration Guide

1. Go to Templates > Media AI Template > Smart Subtitle. The system provides several preset templates that you can use directly, or you can click Create Smart Subtitle Template to create a custom template.

2. Enter the smart subtitle template creation page. The following configuration parameters are supported.

Processing Type of "Generate Subtitles based on ASR"


The following configuration items are supported:
Configuration Item
Description
Template Name
Only Chinese characters, English letters, digits, underscores (_), hyphens (-), and periods (.) are supported, and the length should not exceed 64 characters.
Processing Type
Automatic speech recognition (ASR)-based subtitle generation: Input an audio file or a video file, generate a subtitle file based on ASR, and translate subtitles.
Translation of subtitle files: Input a subtitle file, translate source subtitles to subtitles in different languages through LLM, and generate a new subtitle file.
Processing Type of "ASR-based Subtitle Generation"
Source Language of the Audio Content of the Video
Select the source language of the audio content of the video. The following is a list of the supported source languages.
Associate the ASR Hotword Lexicon
Commonly used words in speech are generally accurately recognized. However, for specific names (such as personal names, product names, and company names) and industry-specific terms (such as the brand name Zhiling, the building name Binhai Dasha, Hebao in the insurance field, or Cunchutong in cloud storage), the recognition accuracy may decrease. To address this issue, we provide a custom hotword lexicon feature. You can add specialized terms through manual input or file import, significantly improving the accuracy of ASR. For detailed configuration guidance, see Custom Hotword Lexicons.
Note:
Currently, the hotword lexicon only supports Mandarin and English. Therefore, the hotword lexicon can only be associated when the source language of the audio content of the video is Simplified Chinese or English.
Enable Translation
After it is enabled, the subtitles in the source language can be translated into the specified language, making it suitable for scenarios such as video translation for global distribution.
Note:
Certain languages are not available for selection currently. If you need to use them, contact us for support.
Target Language for Translation
Subtitle Type
If the translation feature is not enabled, the output subtitles will only contain content in the source language.
When the translation feature is enabled, the following subtitle output types are supported:
Monolingual (target language)
Bilingual (source language + target language)
Subtitle File Format
Currently, the WebVTT and SRT formats are supported. If you only need a subtitle content callback and do not need the output of a subtitle file, you can select Do Not Generate Subtitle Files.

Supported Languages

Processing Type of "Translate Subtitle Files"


Configuration Item
Description
Template Name
Only Chinese characters, English letters, digits, underscores (_), hyphens (-), and periods (.) are supported, and the length should not exceed 64 characters.
Processing Type of "Translation of Subtitle Files"
Source Languages
The default value is "automatic identification". You can also specify a language. The following is a list of the supported source languages.
Target Language for Translation
After it is enabled, the subtitles in the source language can be translated into the specified language, making it suitable for scenarios such as video translation for global distribution. The following is a list of the supported target languages for translation.
Note:
Certain languages are not available for selection currently. If you need to use them, contact us for support.
Subtitle File Format
It is supported to select WebVTT, SRT, or consistent with the source file.
Subtitle Type
The following options are supported:
Monolingual (target language): The generated target language subtitle file contains single-line monolingual subtitles.
Bilingual (source language + target language): The generated target language subtitle file contains dual-line bilingual subtitles.

Supported Languages

Billing Instructions

Billing of the smart subtitle feature is related to the processing type, whether to enable translation, and the number of target languages for translation. Detailed billing scenarios are provided below for reference.

Identifying the Source Language Only and "ASR" Fees Are Charged

If you set the processing type to "ASR-based subtitle generation" without enabling translation, ASR fees will be charged. For pricing details, see Billing Instructions.


Translating the Subtitle to a Target Language, and "Speech Translation" or "Subtitle Translation" Fees Are Charged

If you set the processing type to "ASR-based subtitle generation" with translation enabled, and select a target language for translation, "speech translation" fees will be charged. For pricing details, see Billing Instructions.

If you set the processing type to "Translation of Subtitle Files", and select a target language for translation, "subtitle translation" fees will be charged. For pricing details, see Billing Instructions.


If There Are More Than 1 Target Language for Translation, "Subtitle Translation (Additional Languages)" Fees Will Be Charged for Each Extra Language

If you set the processing type to "ASR-based subtitle generation" with translation enabled, and select n target languages for translation, the fees to be charged are calculated as follows: Speech translation fees × 1 + Subtitle translation (additional languages) fees × (n-1).
Take the following configuration as an example. The fees are calculated as follows: Speech translation fees × 1 + Subtitle translation (additional languages) fees × 3. For pricing details, see Billing Instructions.

If you set the processing type to "Translation of Subtitle Files", and select n target languages for translation, the fees to be charged are calculated as follows: Subtitle translation fees × 1 + Subtitle translation (additional languages) fees × (n-1).
Take the following configuration as an example. The fees to be charged are calculated as follows: Subtitle translation fees × 1 + Subtitle translation (additional languages) fees × 3. For pricing details, see Billing Instructions.


Copyright © 2013-2025 Tencent Cloud. All Rights Reserved.
  1. Privacy Policy
  3. Legal
  5. Cookie Policy