Subtitle Voice Synthesis Software

A software that generates voiceovers from subtitles, utilizing Microsoft's Azure AI neural network Text-to-Speech (TTS) engine.

Multilingual Support

It supports hundreds of languages from over a hundred countries. Each language features characters of different genders and ages, with various speaking styles available for each character.

Human-like Voiceover

Its pronunciation is nearly indistinguishable from that of a real person. Below is a sample of its demonstration voice. The Mandarin Chinese character "Xiaoxiao" can speak multiple languages, all with professional-level fluency.

But my love for this profession is still very strong, heh, very, um, how should I put it? As evident as the sun and moon, haha, um, I still hope to continue in this profession or work in a voice-related field, um, just to maximize my strengths, applying what I excel at, rather than working just for the sake of work or to earn money.

Subtitle Voiceover

Unlike other voiceover software, it supports generating voiceovers based on the timeline of SRT subtitle files. During video production, you simply need to place the generated MP3 file on the timeline to automatically align with the subtitles.

User Guide

• Prepare the SRT subtitle file that needs voiceover
• Select the corresponding language
• Choose the default voice character, which will be used for the entire voiceover file (this can be adjusted for each subtitle line in the editing interface after creation)
• Select voice tone, style, speed, pronunciation, and other parameters
• Click to synthesize and wait for the synthesis to complete
• Download the generated MP3 file