Vrew
Vrew is a free AI-powered video editor by VoyagerX that automatically generates subtitles via speech recognition and lets you edit video by simply editing text.
Vrew is a revolutionary AI-powered video editing application developed by VoyagerX, a South Korean AI startup. First launched in 2018 and continuously improved since, Vrew reimagines what video editing can be by placing speech recognition and AI automation at the heart of the editing experience. It is available as a free desktop application for both Windows and macOS, making professional-quality video editing accessible to everyone.
At the core of Vrew's innovation is its text-based video editing paradigm. When you import a video, Vrew's AI engine automatically transcribes all spoken dialogue into text using advanced speech-to-text (STT) technology. This transcript is then displayed alongside the video timeline, and editing becomes as simple as editing a document — delete a sentence from the transcript and the corresponding video clip is removed automatically. This approach dramatically reduces the time and effort required to cut talking-head videos, lectures, interviews, vlogs, and YouTube content.
Vrew's AI subtitle generation is one of its most celebrated features. The system supports automatic subtitle creation in Korean, English, Japanese, and Chinese, recognizing speech with high accuracy and formatting subtitles with proper line breaks and timing. Subtitles can be extensively customized in terms of font, size, color, background, and position. Once generated, subtitles can be exported in formats including SRT, VTT, and TXT for use in other platforms or broadcast workflows.
Beyond basic editing, Vrew offers a powerful AI voice narration feature that converts any typed text into natural-sounding speech using a variety of AI voices in multiple languages. Content creators who need to add narration without recording their own voice — or who want to produce content in a language they do not speak — find this feature transformative. The text-to-video functionality takes this further, allowing users to generate short video clips from text prompts, opening up new possibilities for presentation and social media content.
Vrew is designed with content creators, YouTubers, educators, corporate trainers, and social media marketers in mind. Its intuitive interface removes the steep learning curve typically associated with video editing software, while its AI features handle the most time-consuming tasks automatically. Whether you are producing Korean YouTube content, educational lectures, corporate training videos, or short-form social content, Vrew provides a fast and accessible path from raw footage to polished, subtitled video.
Key Features
- Automatic subtitle generation using AI speech-to-text (STT) in Korean, English, Japanese, and Chinese
- Text-based video editing — cut clips by deleting sentences from the auto-generated transcript
- AI voice narration — convert typed text to natural-sounding speech with multiple voice options
- Text-to-video generation — create short video clips from text prompts using AI
- Subtitle customization with full control over font, size, color, background, and on-screen position
- Export subtitles in SRT, VTT, and TXT formats for cross-platform compatibility
- Auto-remove silence and filler words (ums, ahs) with a single click to tighten pacing
- B-roll and stock media insertion directly within the editing interface
- Multi-track timeline with support for background music, sound effects, and overlays
- Free desktop app for Windows and macOS with no watermark on exported videos
Frequently Asked Questions
Is Vrew completely free to use?
Yes, Vrew is free to download and use as a desktop application for Windows and macOS. The free plan includes core features such as automatic subtitle generation, text-based video editing, and video export without a watermark. Premium plans are available for users who need longer AI voice narration, higher monthly STT minutes, or additional AI credits for text-to-video generation. For most individual creators and casual users, the free tier is more than sufficient.
How accurate is Vrew's automatic subtitle generation?
Vrew's STT (speech-to-text) accuracy is generally very high, especially for clear speech in Korean, English, Japanese, and Chinese. Korean language recognition is particularly strong given VoyagerX's focus on the Korean market. Accuracy can decrease with heavy accents, overlapping speech, background noise, or highly technical terminology. After auto-generation, the text-based editor makes it easy to quickly review and correct any errors in the transcript before exporting.
What video formats does Vrew support for import and export?
Vrew supports a wide range of common video formats for import, including MP4, MOV, AVI, MKV, and more. For export, you can save as MP4 video with embedded or separate subtitle tracks. Subtitles alone can be exported as SRT, VTT, or plain TXT files. Audio-only export is also supported. The application handles most standard resolutions including 1080p and 4K, making it suitable for both web and broadcast output.
Can I use Vrew to create videos in a language I don't speak?
Yes, this is one of Vrew's most powerful capabilities. Using the AI voice narration feature, you can type a script in Korean, English, Japanese, Chinese, or other supported languages and have Vrew convert it to natural-sounding speech using AI-generated voices. Combined with the subtitle auto-generation, this makes it possible to produce multilingual video content without recording your own voice or hiring voice actors, significantly lowering the barrier to international content creation.
Who is Vrew made by and is it trustworthy?
Vrew is developed by VoyagerX, a well-established South Korean AI startup founded in 2017 by former Naver engineers. The company has received significant investment and recognition within South Korea's tech industry. Vrew has been adopted by millions of users, including major Korean YouTubers, educational institutions, and corporate content teams. It is widely considered the leading AI video editing tool in Korea and has a strong track record of regular updates, active user support, and continuous feature improvements.
Alternative Tools
Other Video tools you might like
CapCut
VideoCapCut is ByteDance's AI-powered video editor dominating short-form content creation, offering auto-captions, background removal, AI effects, and seamless TikTok integration across web, desktop, and mobile.
D-ID
VideoD-ID is an AI digital people platform that animates photos into talking head videos with natural facial expressions and lip sync, enabling real-time streaming avatars for education, marketing, and customer support.
HeyGen
VideoHeyGen is an AI avatar video platform that generates professional videos with photorealistic AI presenters from text scripts in 175+ languages.
InVideo AI
VideoInVideo AI is a text-to-video platform that generates complete marketing and social media videos from prompts, with AI script writing, stock footage selection, voiceover, and subtitles built in.
Kling AI
VideoKling AI is Kuaishou's advanced AI video generation platform, producing up to 2-minute high-quality videos from text or images with realistic motion, physics simulation, and a powerful lip sync feature.
Luma Dream Machine
VideoLuma Dream Machine is an AI video generation model by Luma AI that creates high-quality, physically realistic videos from text and image prompts with remarkably fast generation speeds.
Tags
Related Guides
AI Video Localization Stack for Global Teams in 2026: Rask AI, HeyGen, Synthesia, Descript, and Opus Clip
Last updated: June 22, 2026. The question we keep hearing from marketing and enablement teams is blunt: “Can AI make one good video work in five markets without turning it into cheap-looking sludge?” The answer is yes, but only if you stop treating translation, dubbing, captions, avatars, and short-form editing as separate chores. An AI […]
AI Voice Tools for Podcasts, Training, and Product Videos in 2026: ElevenLabs, Murf, Descript, Suno, and Whisper
Last updated: 2026-06-18 · Category cluster: Audio AI voice tools have crossed the line from novelty demos into daily production. A small team can now record a rough script in the morning, clean the audio before lunch, generate a voiceover in the afternoon, cut a podcast clip before the end of the day, and still […]
AI Short-Form Video Tools in 2026: Turn Webinars, Podcasts, and Demos Into Clips That People Finish
Last updated: June 13, 2026. Written by the findaiverse curation team after testing common webinar, podcast, demo, and social video workflows across current AI video tools. Most teams do not need another spectacular AI video demo. They need a reliable way to turn the videos they already have into clips that people actually finish. A […]
Best AI Tools for Video Production Teams in 2026: A Practical Script-to-Edit Stack
Last updated: June 8, 2026. Written by the findaiverse curation team after comparing current creator workflows, tool pages, and recent AI video coverage. Video teams are no longer asking whether AI belongs in production. They are asking a harder question: which tools actually save time without making every clip look like the same synthetic demo […]