
VovSoft Speech to Subtitle, officially published as Speech to Subtitle Converter, is an offline transcription utility for Windows. Version 2.3 uses Whisper AI and FFmpeg to turn spoken words from audio or video files into synchronized subtitles. Over 100 languages are supported and the transcripts can be saved as SRT, VTT, JSON or even as plain written TXT files.
This tool can be useful for video editors, teachers, journalists, and for podcasters and for all other creators and producers of content, who need written text of spoken words. This utility does not send any media files to any cloud services – all processing is done locally on your computer. If you only need written text of spoken words, you can also look at Vovsoft Speech to Text Converter.
Characteristics of VovSoft Speech to Subtitle
- Creates synchronized subtitles from spoken audio automatically.
- Transcribes video files without extracting audio manually.
- Uses offline Whisper AI for private local processing.
- Supports CPU and GPU-accelerated transcription through FFmpeg.
- Recognizes spoken content in more than 100 languages.
- Accepts MP3, FLAC, WAV, WMA, M4A, and OGG audio.
- Processes MP4, WEBM, MKV, AVI, WMV, TS, and MOV video.
- Exports completed subtitles in SRT and VTT formats.
- Saves structured transcription results as JSON files.
- Creates plain TXT transcripts for notes and articles.
- Generates accurate timestamps for recognized spoken content.
- Works without cloud services or an internet connection.
- Protects sensitive recordings through completely local processing.
- Handles interviews, meetings, lectures, podcasts, and voice memos.
- Available as installer and portable Windows editions.
What’s New in VovSoft Speech to Subtitle 2.3
- Released on July 26, 2026.
- Improved the error details window.
Official Website: VovSoft Speech to Subtitle Official Website
System Requirements
- Operating System: Windows 11 or Windows 10
- Architecture: 32-bit and 64-bit Windows supported
- Graphics: Compatible GPU optional for accelerated transcription
Click here for installation instructions and frequently asked questions
Build Highlights
Software: VovSoft Speech to Subtitle Converter
Type: Official Windows Installer (Silent RePack)
Setup Size: ~154 MB
Status: Clean & Tested